© 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. 6422
    Prev
    Next
    INDEX
    Explanations

    essay, floor plans, introduction, field

    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
     inflamm
    -0.10
     Newman
    -0.10
    /null
    -0.09
     cong
    -0.09
    =explode
    -0.09
    FUL
    -0.09
     USAGE
    -0.09
     GOODMAN
    -0.09
    zes
    -0.08
    rens
    -0.08
    POSITIVE LOGITS
    ocker
    0.08
     Merkel
    0.08
     Wade
    0.08
    orgia
    0.08
     Singular
    0.08
     Concurrent
    0.08
     cuckold
    0.07
    rab
    0.07
     -
    0.07
     cult
    0.07
    Activations Density 0.005%

    No Known Activations