© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115042
    Prev
    Next
    INDEX
    Explanations

    desirable evaluation

    np_acts-logits-general · gemini-2.5-flash-lite

    emotional or evaluative adjectives and adverbs that describe subjective feelings and experiences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demonstr
    -0.10
    dbl
    -0.09
     accum
    -0.09
     sleeps
    -0.09
    ãģĭãĤī
    -0.09
     philosoph
    -0.08
     Trust
    -0.08
     crosses
    -0.08
     detr
    -0.08
     Dude
    -0.08
    POSITIVE LOGITS
     worthwhile
    0.15
     worth
    0.12
     desirable
    0.12
     valued
    0.11
     affirmed
    0.11
     worthy
    0.11
     appreciated
    0.11
    -worthy
    0.11
     validated
    0.11
     targeted
    0.10
    Activations Density 0.010%

    No Known Activations