© 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. 7228
    Prev
    Next
    INDEX
    Explanations

    fanfic, angst, Alam

    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
    ocre
    -0.09
    Posting
    -0.09
     Bookmark
    -0.09
    ầ
    -0.08
     stagn
    -0.08
    ignon
    -0.08
     intimately
    -0.08
     masses
    -0.08
    uggy
    -0.08
    -thinking
    -0.08
    POSITIVE LOGITS
    _excerpt
    0.10
     exh
    0.09
     ordinary
    0.09
    chaft
    0.09
    isz
    0.08
    etti
    0.08
     favor
    0.08
     Aust
    0.08
     homosex
    0.08
     favorite
    0.08
    Activations Density 0.018%

    No Known Activations