© 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. 92092
    Prev
    Next
    INDEX
    Explanations

    acting as a character name

    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
    AGO
    -0.11
    /AFP
    -0.11
     Carp
    -0.11
     Kraft
    -0.11
     outr
    -0.11
    iris
    -0.11
    ONGL
    -0.11
    agoon
    -0.11
     SNAP
    -0.11
    дÑĢ
    -0.10
    POSITIVE LOGITS
    opp
    0.09
    ged
    0.09
    aland
    0.09
    EEP
    0.08
    unan
    0.08
    -v
    0.08
     audible
    0.08
    ien
    0.07
    arda
    0.07
     gratuit
    0.07
    Activations Density 0.003%

    No Known Activations