© 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. 30687
    Prev
    Next
    INDEX
    Explanations

    punk, goth, emo, tattoos

    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
     trot
    -0.12
     cuckold
    -0.12
    pector
    -0.12
     bribery
    -0.12
     jov
    -0.11
     gala
    -0.10
     tennis
    -0.10
    PBS
    -0.10
     NYT
    -0.10
     swimming
    -0.10
    POSITIVE LOGITS
     punk
    0.35
     Goth
    0.32
     Punk
    0.31
    punk
    0.30
     emo
    0.25
     skateboard
    0.24
     anarchist
    0.24
     tattoos
    0.23
     Gothic
    0.23
     tattoo
    0.23
    Activations Density 0.099%

    No Known Activations