© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36508
    Prev
    Next
    INDEX
    Explanations

    Frankly, Frank, Franklin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    æѤåĪ»
    -0.10
    rint
    -0.10
    venth
    -0.09
    angs
    -0.09
    ronic
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    ราà¸ĩ
    -0.09
    lsen
    -0.09
    cret
    -0.09
    roke
    -0.09
    POSITIVE LOGITS
    enstein
    0.19
    fur
    0.12
    ish
    0.11
    furt
    0.11
    ly
    0.11
    enburg
    0.11
    enberg
    0.11
    ../../../
    0.10
    o
    0.10
    lyn
    0.10
    Activations Density 0.020%

    No Known Activations