© 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. 30841
    Prev
    Next
    INDEX
    Explanations

    insert statement

    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
    IFn
    -0.13
     MID
    -0.11
    IDL
    -0.11
    pii
    -0.11
    ez
    -0.11
     lic
    -0.11
    345
    -0.11
     plat
    -0.11
    xc
    -0.10
     exert
    -0.10
    POSITIVE LOGITS
     vivastreet
    0.11
     shitty
    0.09
     fucked
    0.09
     Continued
    0.09
     realtime
    0.08
     fuck
    0.08
     fucks
    0.08
     (↵↵
    0.08
    <|fim_middle|>
    0.08
     "↵↵
    0.07
    Activations Density 0.012%

    No Known Activations