© 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. 3868
    Prev
    Next
    INDEX
    Explanations

    for the sake of

    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
     Kosten
    -0.09
     Spare
    -0.09
    adt
    -0.08
     proceeding
    -0.08
     gangbang
    -0.08
     objection
    -0.08
     gimm
    -0.08
     structured
    -0.08
     twist
    -0.08
    Structured
    -0.07
    POSITIVE LOGITS
     sake
    0.28
     worth
    0.21
     suffice
    0.19
    worth
    0.18
     Worth
    0.18
     Suff
    0.15
     suff
    0.14
     effort
    0.12
    sworth
    0.12
     suf
    0.12
    Activations Density 0.050%

    No Known Activations