© 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. 116248
    Prev
    Next
    INDEX
    Explanations

    size of

    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
     sizes
    -0.09
     complain
    -0.08
    unge
    -0.08
     size
    -0.08
    va
    -0.08
     Bast
    -0.08
    /h
    -0.08
     Ber
    -0.08
    achu
    -0.08
    ugen
    -0.07
    POSITIVE LOGITS
     meas
    0.11
     repertoire
    0.11
    vious
    0.10
    caret
    0.10
    ROID
    0.09
     ваÑĪ
    0.09
    wat
    0.09
     ferment
    0.09
    429
    0.09
     indent
    0.09
    Activations Density 0.040%

    No Known Activations