© 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. 114359
    Prev
    Next
    INDEX
    Explanations

    cyg, cyrt, hyer, cython, cyclosporine

    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
    àµįà´
    -0.13
    uale
    -0.12
    idad
    -0.12
    ni
    -0.11
    itis
    -0.11
    inia
    -0.11
    ocs
    -0.11
    nelle
    -0.11
    no
    -0.10
    nick
    -0.10
    POSITIVE LOGITS
     yi
    0.10
    ther
    0.09
    dra
    0.09
    ders
    0.09
     gio
    0.08
    der
    0.08
     Yi
    0.08
    kker
    0.08
    ö
    0.08
    oser
    0.08
    Activations Density 0.085%

    No Known Activations