© 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. 32537
    Prev
    Next
    INDEX
    Explanations

    Product Information

    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
    ense
    -0.07
     enamel
    -0.07
     SEL
    -0.07
    acre
    -0.07
    iring
    -0.07
     barg
    -0.07
    anim
    -0.07
     scanned
    -0.07
    ashes
    -0.07
     anim
    -0.07
    POSITIVE LOGITS
    ftime
    0.11
    олн
    0.11
    RICS
    0.11
     exagger
    0.11
     Budget
    0.11
    uso
    0.10
    ITU
    0.10
     vid
    0.10
     InputStream
    0.10
     Freeze
    0.10
    Activations Density 0.016%

    No Known Activations