© 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. 25762
    Prev
    Next
    INDEX
    Explanations

    websites

    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
    oretical
    -0.10
    <|fim_suffix|>
    -0.08
    rap
    -0.08
     Ale
    -0.08
    eenth
    -0.08
     Crowley
    -0.08
     conjug
    -0.08
     prostit
    -0.07
    Ale
    -0.07
     golden
    -0.07
    POSITIVE LOGITS
    ohl
    0.11
    cdr
    0.11
     acc
    0.10
    attr
    0.10
    opp
    0.09
     kut
    0.09
    аÑĩ
    0.09
    acc
    0.09
    Esp
    0.09
     LB
    0.09
    Activations Density 0.058%

    No Known Activations