© 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. 17989
    Prev
    Next
    INDEX
    Explanations

    end of comment or post

    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
    âĢ¦↵↵↵↵
    -0.12
    esa
    -0.10
     isl
    -0.09
    ↵↵↵↵
    -0.08
    Č
    -0.08
    <|endoftext|>
    -0.08
     Bien
    -0.08
    <|fim_middle|>
    -0.08
    -ok
    -0.08
    illow
    -0.08
    POSITIVE LOGITS
     Reply
    0.19
    Reply
    0.16
     reply
    0.16
     replied
    0.13
     Comment
    0.13
     commenter
    0.13
     Posted
    0.11
     Replies
    0.11
     Likes
    0.11
     comment
    0.11
    Activations Density 0.097%

    No Known Activations