© 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. 89542
    Prev
    Next
    INDEX
    Explanations

    suffix endings

    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
    usk
    -0.10
     Hund
    -0.10
    str
    -0.10
     ass
    -0.10
     Delaware
    -0.10
    UGE
    -0.09
    voy
    -0.09
    Ark
    -0.09
    @[
    -0.09
     Cargo
    -0.09
    POSITIVE LOGITS
     syn
    0.10
    ;
    0.10
     habit
    0.09
     Syn
    0.09
     distinguished
    0.09
     blamed
    0.09
     collectively
    0.09
    ited
    0.08
     contrast
    0.08
     unspecified
    0.08
    Activations Density 0.284%

    No Known Activations