© 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. 90337
    Prev
    Next
    INDEX
    Explanations

    recreation, games, functions, types

    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
    aylor
    -0.07
    vet
    -0.07
    ,**
    -0.06
     Bradley
    -0.06
    infos
    -0.06
     w
    -0.06
    esi
    -0.06
     Nah
    -0.06
    iza
    -0.06
     ain
    -0.06
    POSITIVE LOGITS
     hail
    0.11
    ķìĿ¸
    0.11
     basal
    0.11
    .xr
    0.11
     summons
    0.11
    MEDIA
    0.10
     Chatt
    0.10
     ë¡
    0.10
     Monaco
    0.10
    .tex
    0.10
    Activations Density 0.083%

    No Known Activations