© 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. 17909
    Prev
    Next
    INDEX
    Explanations

    separators and special characters

    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
    ~↵
    -0.11
    chet
    -0.09
    ~↵↵
    -0.09
    âĻª
    -0.09
     -↵
    -0.09
    /**<
    -0.09
     jorn
    -0.09
     stubborn
    -0.09
     ..↵
    -0.09
     ~
    -0.08
    POSITIVE LOGITS
    ++++
    0.13
     PPP
    0.13
    +++
    0.13
    PPP
    0.13
    ooo
    0.12
    oooo
    0.11
     Percy
    0.11
    cccc
    0.11
     AAA
    0.11
    ccc
    0.11
    Activations Density 0.346%

    No Known Activations