© 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. 113044
    Prev
    Next
    INDEX
    Explanations

    code templating syntax or curse words

    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
     lux
    -0.08
     unn
    -0.08
    yar
    -0.08
    prd
    -0.07
     Edison
    -0.07
     Shoes
    -0.06
     attire
    -0.06
    ritis
    -0.06
    ptom
    -0.06
    CEL
    -0.06
    POSITIVE LOGITS
    e
    0.16
    ily
    0.13
    tick
    0.13
    touch
    0.12
    ega
    0.12
    ucking
    0.12
    tap
    0.12
    fully
    0.12
    ey
    0.12
    tion
    0.12
    Activations Density 0.002%

    No Known Activations