© 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. 113934
    Prev
    Next
    INDEX
    Explanations

    induced + states or effects

    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
    sf
    -0.10
    lette
    -0.10
    acci
    -0.09
    asan
    -0.09
    396
    -0.09
    atten
    -0.09
     Mein
    -0.09
     unfavor
    -0.08
     cha
    -0.08
     Summers
    -0.08
    POSITIVE LOGITS
     trance
    0.14
     paralysis
    0.12
     coma
    0.12
     panic
    0.11
     frenzy
    0.11
     hysteria
    0.11
    Into
    0.10
     guilt
    0.10
     blindness
    0.10
    _Tr
    0.10
    Activations Density 0.110%

    No Known Activations