© 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. 16168
    Prev
    Next
    INDEX
    Explanations

    title followed by colon or text

    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
     gov
    -0.10
    ester
    -0.08
    oca
    -0.08
    archy
    -0.08
     SX
    -0.08
     partially
    -0.08
     mailing
    -0.08
     receipt
    -0.08
     dist
    -0.08
    /false
    -0.08
    POSITIVE LOGITS
    Subtitle
    0.12
    .subtitle
    0.10
    >Title
    0.10
     IX
    0.10
     VII
    0.10
    η
    0.10
    sted
    0.10
     Penalty
    0.10
    umph
    0.10
    umas
    0.10
    Activations Density 0.021%

    No Known Activations