© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6307
    Prev
    Next
    INDEX
    Explanations

    HTML entities and character codes like `&#x`, `&#880`, `&#116`

    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
    aldi
    -0.10
    achs
    -0.09
     ball
    -0.09
    enton
    -0.09
     sleeve
    -0.09
    /LICENSE
    -0.09
     Jacques
    -0.09
     dial
    -0.08
    rapy
    -0.08
    chn
    -0.08
    POSITIVE LOGITS
     rall
    0.10
    oyer
    0.10
    Reviewer
    0.10
     Gong
    0.09
    oon
    0.09
     fullname
    0.09
    oola
    0.09
    GOR
    0.09
    oom
    0.09
     colon
    0.09
    Activations Density 0.005%

    No Known Activations