© 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. 48928
    Prev
    Next
    INDEX
    Explanations

    line of sight

    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
     Bien
    -0.10
     scheduled
    -0.10
     Placeholder
    -0.10
    immers
    -0.10
    ema
    -0.09
    /var
    -0.09
    è½
    -0.09
    JD
    -0.09
    ADM
    -0.09
     ind
    -0.09
    POSITIVE LOGITS
    adors
    0.09
     preventing
    0.09
     aisle
    0.08
     path
    0.08
    aggio
    0.08
    Behind
    0.08
     Behind
    0.08
     position
    0.08
     afforded
    0.08
    Position
    0.08
    Activations Density 0.070%

    No Known Activations