© 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. 16781
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by positive action

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    esor
    -0.11
     workings
    -0.11
     kadar
    -0.11
    \↵
    -0.11
     hil
    -0.10
     unfamiliar
    -0.10
    assi
    -0.10
     Ended
    -0.10
    <?↵
    -0.10
    polate
    -0.10
    POSITIVE LOGITS
     become
    0.11
     relax
    0.10
     enjoy
    0.09
     Relax
    0.09
     gain
    0.08
     embrace
    0.08
     sharpen
    0.07
    rel
    0.07
     prosper
    0.07
     reap
    0.07
    Activations Density 0.050%

    No Known Activations