© 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. 88586
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     obscene
    -0.13
     Cox
    -0.09
     explicit
    -0.09
    rito
    -0.09
     activations
    -0.09
     Funk
    -0.09
    anst
    -0.09
     passe
    -0.09
     Ras
    -0.08
    DO
    -0.08
    POSITIVE LOGITS
     Mutual
    0.08
     partially
    0.08
    ugo
    0.08
     adjective
    0.08
     Destination
    0.08
    _ent
    0.08
    ankan
    0.08
    (Screen
    0.08
     entrenched
    0.08
     Study
    0.08
    Activations Density 0.051%

    No Known Activations