© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92296
    Prev
    Next
    INDEX
    Explanations

    timestamps and numbers

    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
     superf
    -0.12
    erde
    -0.11
    /Test
    -0.11
    erset
    -0.10
    anj
    -0.10
    bsolute
    -0.10
    /part
    -0.10
     unre
    -0.10
    uada
    -0.10
    ож
    -0.10
    POSITIVE LOGITS
    bout
    0.07
    addy
    0.07
     al
    0.07
    _struct
    0.07
     torpedo
    0.07
    toa
    0.07
     bay
    0.07
     qw
    0.06
     telefon
    0.06
     bout
    0.06
    Activations Density 0.002%

    No Known Activations