© 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. 46497
    Prev
    Next
    INDEX
    Explanations

    caucasus

    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
    ahren
    -0.10
     Moved
    -0.10
    itten
    -0.10
    ossal
    -0.10
    aces
    -0.10
     phil
    -0.09
     Seen
    -0.09
     lowering
    -0.09
    ORK
    -0.09
    anmar
    -0.09
    POSITIVE LOGITS
    hoot
    0.14
    fé
    0.13
    hya
    0.12
    utions
    0.12
    UTION
    0.11
    h
    0.11
    hill
    0.10
    ucas
    0.10
    ult
    0.10
    USE
    0.10
    Activations Density 0.092%

    No Known Activations