© 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. 90173
    Prev
    Next
    INDEX
    Explanations

    from a place or source

    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
     Geoffrey
    -0.10
    Tit
    -0.09
     Misc
    -0.09
    isman
    -0.08
    err
    -0.08
    ós
    -0.08
    "c
    -0.08
    dam
    -0.08
    Pen
    -0.08
    imm
    -0.08
    POSITIVE LOGITS
    odia
    0.12
     saddle
    0.11
     whence
    0.11
     pillar
    0.10
    enden
    0.10
     place
    0.09
     grasp
    0.09
    odi
    0.09
    ç¬
    0.09
    ippy
    0.09
    Activations Density 0.019%

    No Known Activations