© 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. 27608
    Prev
    Next
    INDEX
    Explanations

    image, file, or attribute properties

    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
     forb
    -0.07
     insol
    -0.07
     mitt
    -0.07
     seeming
    -0.07
     envisioned
    -0.07
     inline
    -0.07
     Mot
    -0.07
     guise
    -0.07
     unthinkable
    -0.07
    skins
    -0.07
    POSITIVE LOGITS
    less
    0.14
     popping
    0.13
     correction
    0.12
     bleeding
    0.12
    -only
    0.12
    LESS
    0.12
    æĴ
    0.11
     explodes
    0.11
    ,body
    0.11
     manipulation
    0.11
    Activations Density 0.015%

    No Known Activations