© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18828
    Prev
    Next
    INDEX
    Explanations

    Clayton, Clay City, Clay County

    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
    isable
    -0.11
    aphore
    -0.09
    naire
    -0.09
    ä¸Ģ件
    -0.08
    еÑĤÑĮ
    -0.08
    åħīéĺ´
    -0.08
     назад
    -0.08
    è¿Ļ件
    -0.08
    ëĦ¤
    -0.08
    éc
    -0.08
    POSITIVE LOGITS
    ish
    0.10
    ãĥĥãĤ·ãĥ¥
    0.10
    bout
    0.10
    rador
    0.10
    room
    0.10
     dá»±ng
    0.10
    orte
    0.10
    mates
    0.10
    ervo
    0.10
    æ¸Ĭ
    0.10
    Activations Density 0.007%

    No Known Activations