© 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. 116224
    Prev
    Next
    INDEX
    Explanations

    company, club, sport, society, agency, player

    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
    endor
    -0.10
    engu
    -0.09
    ombo
    -0.09
    odon
    -0.09
    [assembly
    -0.09
    athom
    -0.08
     Suns
    -0.08
     disappe
    -0.08
     SOUND
    -0.08
     Bened
    -0.08
    POSITIVE LOGITS
     whom
    0.26
     beloved
    0.23
     whose
    0.20
     that
    0.18
     which
    0.16
     familiar
    0.16
    whose
    0.15
     коÑĤоÑĢÑĭй
    0.14
     cherished
    0.14
     коÑĤоÑĢ
    0.13
    Activations Density 0.433%

    No Known Activations