© 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. 46861
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    agers
    -0.10
     chance
    -0.08
     slugg
    -0.07
    CAC
    -0.07
     Bale
    -0.07
     Schwar
    -0.07
    /column
    -0.07
     Schwarz
    -0.07
    agraph
    -0.07
    .TypeOf
    -0.07
    POSITIVE LOGITS
    rement
    0.11
    ly
    0.11
    ric
    0.11
    mented
    0.10
     +#+
    0.10
    arness
    0.10
    uego
    0.09
    uries
    0.09
    ilen
    0.09
    dden
    0.09
    Activations Density 0.532%

    No Known Activations