© 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. 33322
    Prev
    Next
    INDEX
    Explanations

    year, date, version

    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
    sez
    -0.10
     Hag
    -0.10
     Shadows
    -0.10
    ane
    -0.09
    way
    -0.09
    hl
    -0.08
    lp
    -0.08
    hq
    -0.08
    TY
    -0.08
    undo
    -0.08
    POSITIVE LOGITS
    -present
    0.21
    ëħ
    0.21
    å¹´
    0.21
    âĢ³
    0.18
     onwards
    0.14
    âĢ²
    0.13
    -era
    0.12
     г
    0.12
     edition
    0.11
    -'
    0.11
    Activations Density 0.669%

    No Known Activations