© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49886
    Prev
    Next
    INDEX
    Explanations

    avoidance, of, box, cell, variance

    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
     predecess
    -0.07
     Bradford
    -0.07
    ston
    -0.06
     DSL
    -0.06
    Anderson
    -0.06
     vulner
    -0.06
     roma
    -0.05
     KR
    -0.05
     RTL
    -0.05
     tall
    -0.05
    POSITIVE LOGITS
     Fur
    0.11
     Fus
    0.10
    cob
    0.10
     mentre
    0.10
    erable
    0.09
    StateException
    0.09
     Nom
    0.09
     Riv
    0.09
     вÑĭп
    0.09
     Blanch
    0.09
    Activations Density 2.681%

    No Known Activations