© 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. 91956
    Prev
    Next
    INDEX
    Explanations

    Vito, scream, busters, throat

    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
    atron
    -0.09
    izable
    -0.08
     Apt
    -0.08
     Lub
    -0.08
    able
    -0.08
     greatly
    -0.07
    akov
    -0.07
     outf
    -0.07
     erot
    -0.07
    zon
    -0.07
    POSITIVE LOGITS
    (er
    0.16
    /small
    0.14
    /big
    0.14
     stature
    0.13
    -headed
    0.12
     Enough
    0.11
    /fast
    0.11
    (est
    0.11
     ass
    0.11
    abee
    0.11
    Activations Density 0.020%

    No Known Activations