© 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. 89227
    Prev
    Next
    INDEX
    Explanations

    the [object]

    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
     bury
    -0.09
     conc
    -0.09
     forthcoming
    -0.09
     Conc
    -0.09
     bou
    -0.09
     buried
    -0.08
    coc
    -0.08
     scopes
    -0.08
     faces
    -0.08
     Erl
    -0.08
    POSITIVE LOGITS
     neatly
    0.13
    ufe
    0.13
     offending
    0.13
     expended
    0.12
     intact
    0.12
     now
    0.11
     limp
    0.11
     washed
    0.11
     unchanged
    0.11
     useless
    0.10
    Activations Density 0.069%

    No Known Activations