© 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. 4227
    Prev
    Next
    INDEX
    Explanations

    Hick, Wick, Mick, Vick, lick

    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
    edo
    -0.12
    ed
    -0.12
    er
    -0.11
     distant
    -0.09
    egis
    -0.08
    ICS
    -0.08
     absolute
    -0.08
    ing
    -0.08
    ger
    -0.08
    haft
    -0.08
    POSITIVE LOGITS
    leness
    0.17
    ety
    0.13
    a
    0.12
    tion
    0.12
    afort
    0.12
    ened
    0.12
    named
    0.12
    lick
    0.11
    nell
    0.11
    starter
    0.11
    Activations Density 0.050%

    No Known Activations