© 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. 32105
    Prev
    Next
    INDEX
    Explanations

    Parmesan, arm, erm

    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
    eral
    -0.09
    lem
    -0.08
    ver
    -0.08
    on
    -0.08
    h
    -0.08
    za
    -0.08
    ilde
    -0.07
    erge
    -0.07
    nin
    -0.07
    ni
    -0.07
    POSITIVE LOGITS
     jun
    0.12
    aby
    0.12
    ament
    0.12
    aments
    0.12
    HAM
    0.12
    elige
    0.12
    esan
    0.12
    wide
    0.11
    icamente
    0.11
     mole
    0.11
    Activations Density 0.002%

    No Known Activations