© 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. 32011
    Prev
    Next
    INDEX
    Explanations

    Spencer

    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
    ————————
    -0.11
    lm
    -0.11
    bles
    -0.11
     Qué
    -0.11
    onor
    -0.11
    orro
    -0.11
    uted
    -0.10
    stalk
    -0.10
    ural
    -0.10
     vit
    -0.10
    POSITIVE LOGITS
    eti
    0.09
    ates
    0.08
    ian
    0.08
     singular
    0.08
    appa
    0.08
    etime
    0.08
    ÑıÑĤÑĮ
    0.07
    ivy
    0.07
    eto
    0.07
    idth
    0.07
    Activations Density 0.010%

    No Known Activations