© 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. 4758
    Prev
    Next
    INDEX
    Explanations

    permission granted or denied

    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
    thew
    -0.10
    ting
    -0.09
    imes
    -0.09
    erv
    -0.09
    rary
    -0.09
    acious
    -0.09
     occasion
    -0.09
     Shuffle
    -0.09
     Dana
    -0.09
    ument
    -0.09
    POSITIVE LOGITS
     granted
    0.16
     Granted
    0.14
    /access
    0.12
    _GRANTED
    0.12
     slip
    0.12
    /license
    0.12
    /right
    0.12
    -seeking
    0.12
    (permission
    0.12
    /notification
    0.11
    Activations Density 0.029%

    No Known Activations