© 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. 27754
    Prev
    Next
    INDEX
    Explanations

    all kinds/types/sorts

    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
     ank
    -0.10
    avar
    -0.10
    ÑĤоÑĢ
    -0.09
    IDA
    -0.08
     vero
    -0.08
     Rub
    -0.08
    tee
    -0.08
    chine
    -0.08
    allee
    -0.08
    arking
    -0.08
    POSITIVE LOGITS
     sorts
    0.28
     kinds
    0.25
     sort
    0.21
     manner
    0.20
     kind
    0.20
     imaginable
    0.20
     SORT
    0.19
     conceivable
    0.17
     KIND
    0.16
    sort
    0.15
    Activations Density 0.086%

    No Known Activations