© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26910
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    etCode
    -0.08
     ero
    -0.08
     neh
    -0.08
     Erotik
    -0.08
     Ngb
    -0.08
     vere
    -0.07
    <|fim_suffix|>
    -0.07
     ime
    -0.07
    Sync
    -0.07
    <|fim_middle|>
    -0.07
    POSITIVE LOGITS
    _marshall
    0.14
     limburg
    0.12
     $__
    0.11
     aalborg
    0.11
     geral
    0.11
     Fields
    0.11
    stras
    0.11
     dando
    0.10
     donner
    0.10
     Noticed
    0.10
    Activations Density 0.116%

    No Known Activations