© 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. 90981
    Prev
    Next
    INDEX
    Explanations

    help us or him

    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
     heck
    -0.09
     comm
    -0.09
    ogg
    -0.09
    ga
    -0.09
    uju
    -0.09
     Suff
    -0.08
     mux
    -0.08
    LEM
    -0.08
    ect
    -0.08
     sole
    -0.08
    POSITIVE LOGITS
     helping
    0.13
     Helping
    0.12
    .Help
    0.12
    /help
    0.12
    æ²»
    0.11
    [assembly
    0.11
     helped
    0.11
     perpet
    0.10
     rehabilit
    0.10
    /cop
    0.10
    Activations Density 0.044%

    No Known Activations