© 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. 17514
    Prev
    Next
    INDEX
    Explanations

    mail.v or mail.ch

    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
    zn
    -0.08
     ding
    -0.08
    erah
    -0.08
     forward
    -0.08
    ager
    -0.08
    ambi
    -0.08
    unner
    -0.08
     Rom
    -0.08
    argin
    -0.08
    Âł
    -0.08
    POSITIVE LOGITS
     peg
    0.10
     leash
    0.10
     pec
    0.10
     Hast
    0.09
     telegram
    0.08
     Fucking
    0.08
    obs
    0.08
     mand
    0.08
     peculiar
    0.08
    uset
    0.08
    Activations Density 0.185%

    No Known Activations