© 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. 91036
    Prev
    Next
    INDEX
    Explanations

    punctuation and separators

    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
    insky
    -0.08
     [...]
    -0.08
    ichten
    -0.07
    jaw
    -0.07
     ``
    -0.07
     forte
    -0.07
     generic
    -0.07
    l
    -0.07
     (...)
    -0.07
    ,and
    -0.07
    POSITIVE LOGITS
    uner
    0.11
    ahr
    0.10
    igy
    0.10
     $č↵
    0.10
     Smy
    0.10
    gni
    0.10
     artwork
    0.10
    ÑĢан
    0.10
    /msg
    0.10
     Thorn
    0.10
    Activations Density 0.002%

    No Known Activations