© 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. 5886
    Prev
    Next
    INDEX
    Explanations

    l followed by inq

    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
    ìľ¼ë¡ľ
    -0.12
    elda
    -0.11
    els
    -0.11
    elta
    -0.10
    ogg
    -0.10
    reen
    -0.09
    elle
    -0.09
    ete
    -0.09
    eld
    -0.09
    ork
    -0.09
    POSITIVE LOGITS
    wjgl
    0.18
    ateral
    0.18
    abeled
    0.15
    amination
    0.14
    ollipop
    0.14
    alive
    0.14
    igation
    0.14
    ively
    0.14
    ighthouse
    0.14
    enght
    0.13
    Activations Density 0.229%

    No Known Activations