© 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. 91404
    Prev
    Next
    INDEX
    Explanations

    Tan or tan

    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
    ed
    -0.12
    aign
    -0.11
    ened
    -0.11
    aub
    -0.10
    ted
    -0.10
    isch
    -0.09
    ended
    -0.09
    anness
    -0.09
    eled
    -0.09
    tion
    -0.09
    POSITIVE LOGITS
    aka
    0.11
    DEM
    0.11
     sess
    0.10
     tantr
    0.10
    anka
    0.09
    Tan
    0.09
    wand
    0.09
    agra
    0.09
    rts
    0.09
    tri
    0.09
    Activations Density 0.006%

    No Known Activations