© 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. 49393
    Prev
    Next
    INDEX
    Explanations

    than ever

    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
     Dread
    -0.11
    wm
    -0.10
    umber
    -0.09
     Witt
    -0.09
    "$
    -0.09
    ghest
    -0.09
     dread
    -0.08
    SOR
    -0.08
     SEAL
    -0.08
     SHORT
    -0.08
    POSITIVE LOGITS
     not
    0.27
    not
    0.23
     Not
    0.20
    	not
    0.18
    -not
    0.18
    Not
    0.17
    _not
    0.17
    .not
    0.17
     NOT
    0.17
    (not
    0.16
    Activations Density 0.014%

    No Known Activations