© 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. 91834
    Prev
    Next
    INDEX
    Explanations

    him/her/them to

    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
     widow
    -0.08
    deps
    -0.07
     slipped
    -0.07
     surprise
    -0.07
     Yao
    -0.07
     detailed
    -0.07
    477
    -0.06
     Exp
    -0.06
     tricky
    -0.06
    ning
    -0.06
    POSITIVE LOGITS
     badly
    0.15
     desperately
    0.14
    estroy
    0.13
     desper
    0.13
     clap
    0.12
     alive
    0.11
     thrott
    0.11
     dead
    0.11
    quia
    0.11
     dearly
    0.11
    Activations Density 0.016%

    No Known Activations