© 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. 26287
    Prev
    Next
    INDEX
    Explanations

    form

    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
    imits
    -0.09
     Trusted
    -0.09
     Frid
    -0.09
     ffi
    -0.09
     IMO
    -0.09
    arty
    -0.08
    elin
    -0.08
     ignorant
    -0.08
     elm
    -0.08
    umo
    -0.08
    POSITIVE LOGITS
    .self
    0.10
     Seventh
    0.10
    gard
    0.10
     solid
    0.09
    à¸ĸ
    0.09
    897
    0.09
    oons
    0.09
     groom
    0.09
     Hedge
    0.09
    osc
    0.09
    Activations Density 0.001%

    No Known Activations