© 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. 114398
    Prev
    Next
    INDEX
    Explanations

    mad- at the start of words

    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
    lectric
    -0.07
     duty
    -0.07
    ç±
    -0.07
     yg
    -0.07
    .atom
    -0.07
    ulative
    -0.07
    JKLM
    -0.07
     assisting
    -0.07
    .Buffered
    -0.07
    905
    -0.07
    POSITIVE LOGITS
     Mad
    0.10
     afore
    0.10
     mad
    0.10
    Mad
    0.10
     ire
    0.09
     embarrass
    0.09
    mad
    0.09
    lsa
    0.09
     stare
    0.08
    ADIUS
    0.08
    Activations Density 0.064%

    No Known Activations