© 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. 114408
    Prev
    Next
    INDEX
    Explanations

    ah, alive, chorus, yeah

    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
    PLUS
    -0.09
     Eid
    -0.09
     plus
    -0.09
    _self
    -0.09
    Plus
    -0.09
     unicorn
    -0.09
     Fle
    -0.09
     'č↵
    -0.09
    /script
    -0.09
    POSITIVE LOGITS
     yeah
    0.15
    yeah
    0.13
     Yeah
    0.12
    âĻª↵↵
    0.11
     oh
    0.11
     chorus
    0.10
     Lyrics
    0.10
     Everybody
    0.10
    Everybody
    0.10
     repeat
    0.10
    Activations Density 0.070%

    No Known Activations