© 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. 14243
    Prev
    Next
    INDEX
    Explanations

    that enables

    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
    quire
    -0.08
     recurs
    -0.08
    ucker
    -0.08
    yer
    -0.08
     Packs
    -0.08
    lug
    -0.08
    lov
    -0.08
     exert
    -0.07
     Appeals
    -0.07
     undergo
    -0.07
    POSITIVE LOGITS
     allow
    0.23
     allows
    0.22
     enables
    0.19
     enable
    0.18
     permet
    0.17
     Allow
    0.17
     lets
    0.16
     let
    0.16
    allow
    0.16
    allows
    0.15
    Activations Density 0.437%

    No Known Activations