© 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. 113899
    Prev
    Next
    INDEX
    Explanations

    anal play; section; nulls

    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
     lodged
    -0.08
    ewed
    -0.08
     pit
    -0.08
     embar
    -0.07
    igned
    -0.07
     muscle
    -0.07
     Muscle
    -0.07
     Interr
    -0.07
     Mov
    -0.07
     circulated
    -0.07
    POSITIVE LOGITS
    itte
    0.11
    OPY
    0.11
    imm
    0.10
     Zwe
    0.10
    isode
    0.10
     exploration
    0.10
     unprotected
    0.10
    766
    0.10
     experimentation
    0.10
    ogg
    0.10
    Activations Density 0.003%

    No Known Activations