© 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. 7175
    Prev
    Next
    INDEX
    Explanations

    specific aims, error, solution, worries, ally

    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
     specific
    -0.14
    _specific
    -0.14
    Specific
    -0.12
    specific
    -0.12
    pecific
    -0.11
     swiftly
    -0.11
    ful
    -0.11
     specify
    -0.11
     specified
    -0.10
    ey
    -0.10
    POSITIVE LOGITS
    ally
    0.28
    ALLY
    0.22
    ities
    0.21
    ially
    0.19
    ity
    0.16
    -purpose
    0.16
    ITY
    0.14
    iation
    0.14
    iations
    0.13
    ively
    0.13
    Activations Density 0.103%

    No Known Activations