© 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. 116902
    Prev
    Next
    INDEX
    Explanations

    mentions listing or descriptions

    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
     imitation
    -0.10
    edd
    -0.10
    iland
    -0.10
    rire
    -0.09
     yell
    -0.08
     conversation
    -0.08
     listeners
    -0.08
     ribbon
    -0.08
     Conversation
    -0.08
     Episode
    -0.08
    POSITIVE LOGITS
     listed
    0.31
     mentions
    0.26
     mention
    0.25
     paragraph
    0.25
     descriptions
    0.25
     Listed
    0.24
     footnote
    0.24
     reading
    0.24
    listed
    0.22
     paragraphs
    0.22
    Activations Density 0.425%

    No Known Activations