© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90135
    Prev
    Next
    INDEX
    Explanations

    special characters followed by code or punctuation

    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
     gar
    -0.09
     rallied
    -0.08
     Demp
    -0.08
     Garrett
    -0.08
     sh
    -0.07
     ech
    -0.07
    rost
    -0.07
     —
    -0.07
    zion
    -0.07
     tot
    -0.07
    POSITIVE LOGITS
     Vend
    0.12
     Budd
    0.11
     ISI
    0.11
     @_
    0.11
     typealias
    0.10
     consum
    0.10
     Joi
    0.10
     Immutable
    0.10
     Breed
    0.10
     dun
    0.10
    Activations Density 0.079%

    No Known Activations