© 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. 32439
    Prev
    Next
    INDEX
    Explanations

    terms of license

    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
    568
    -0.10
    thood
    -0.09
     and
    -0.09
    .—
    -0.09
     s
    -0.09
    ;
    -0.09
    -vs
    -0.08
    Berry
    -0.08
    .
    -0.08
    ,
    -0.08
    POSITIVE LOGITS
    /Dk
    0.11
    /INFO
    0.10
     FAC
    0.10
    "struct
    0.10
    ->↵
    0.09
     lesb
    0.09
     grav
    0.09
     Stern
    0.09
     Gratis
    0.09
     seks
    0.09
    Activations Density 0.087%

    No Known Activations