© 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. 50037
    Prev
    Next
    INDEX
    Explanations

    shutting or shutout

    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
     Mam
    -0.08
    hem
    -0.08
    ity
    -0.08
    hed
    -0.07
    akis
    -0.07
    achs
    -0.07
    leen
    -0.07
    bour
    -0.07
    hq
    -0.07
    rint
    -0.07
    POSITIVE LOGITS
    ters
    0.23
    ting
    0.18
     down
    0.17
     shut
    0.17
    tings
    0.16
    cheon
    0.16
    ty
    0.16
    -down
    0.16
    _RDWR
    0.16
    icle
    0.14
    Activations Density 0.008%

    No Known Activations