© 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. 91359
    Prev
    Next
    INDEX
    Explanations

    mystery novels author

    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
     discipl
    -0.09
     Hulk
    -0.08
     Cosmic
    -0.07
     Fon
    -0.07
     Wolverine
    -0.07
     ensl
    -0.07
     FCC
    -0.07
    /il
    -0.07
    FML
    -0.07
    abbo
    -0.07
    POSITIVE LOGITS
     forensic
    0.30
     crime
    0.26
     Crime
    0.25
    Crime
    0.24
     homicide
    0.24
     Criminal
    0.23
     FBI
    0.22
     Detective
    0.22
    crime
    0.21
     detectives
    0.21
    Activations Density 2.191%

    No Known Activations