© 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. 5153
    Prev
    Next
    INDEX
    Explanations

    labels or metadata following colons

    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
     Archived
    -0.12
    /live
    -0.12
    .âĢ¦↵↵
    -0.12
    /auto
    -0.12
     âĨĴ↵↵
    -0.11
     Juli
    -0.11
    Hits
    -0.11
    <|endoftext|>
    -0.11
     Ole
    -0.11
    atta
    -0.11
    POSITIVE LOGITS
    (s
    0.11
     preferably
    0.08
     creds
    0.07
     blasph
    0.07
    ikt
    0.07
     forthcoming
    0.07
     ditch
    0.07
    /R
    0.07
    /A
    0.06
    :
    0.06
    Activations Density 0.306%

    No Known Activations