© 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. 14557
    Prev
    Next
    INDEX
    Explanations

    permit or permitted

    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
    -0.10
    /big
    -0.10
     composite
    -0.10
    rlen
    -0.10
    ses
    -0.10
    /met
    -0.10
    ora
    -0.10
    _GB
    -0.10
    plode
    -0.10
    eri
    -0.09
    POSITIVE LOGITS
    tee
    0.15
    tees
    0.14
    ting
    0.11
    ter
    0.09
     Granted
    0.09
    /res
    0.09
    Denied
    0.09
    ably
    0.09
    /license
    0.09
    entious
    0.09
    Activations Density 0.046%

    No Known Activations