© 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. 27497
    Prev
    Next
    INDEX
    Explanations

    web file extension after index

    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
    Indices
    -0.08
     indexes
    -0.07
    eken
    -0.07
    erty
    -0.07
     clickable
    -0.07
    itten
    -0.07
     diss
    -0.07
     comm
    -0.07
    Indexes
    -0.07
    onth
    -0.07
    POSITIVE LOGITS
    ordo
    0.13
    upt
    0.13
     Vote
    0.12
    lags
    0.11
    conj
    0.11
    agens
    0.11
     Heading
    0.11
     bapt
    0.11
     MethodInvocation
    0.10
     deser
    0.10
    Activations Density 0.011%

    No Known Activations