© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    section introduction marker

    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
     (↵↵
    -0.09
     originals
    -0.08
     Vul
    -0.08
     Acres
    -0.08
    Č↵
    -0.07
     yer
    -0.07
     lvl
    -0.07
    <|fim_suffix|>
    -0.07
     relative
    -0.07
     CRT
    -0.07
    POSITIVE LOGITS
    :
    0.12
    arkin
    0.12
    arkan
    0.11
    786
    0.10
    emma
    0.10
    akte
    0.10
    :maj
    0.10
    infeld
    0.10
    Singleton
    0.10
    ambre
    0.10
    Activations Density 0.197%

    No Known Activations