© 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. 28082
    Prev
    Next
    INDEX
    Explanations

    vacancies

    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
     TÃłi
    -0.09
     PROGMEM
    -0.09
    èĤ©
    -0.08
    åľ¨äº¬
    -0.08
    strap
    -0.08
    èĻ¹
    -0.08
    imum
    -0.08
    京
    -0.08
    ä¸įæĸŃå¢ŀ强
    -0.08
    scribe
    -0.08
    POSITIVE LOGITS
    amon
    0.09
    åħ¶æīĢ
    0.09
    è¶ģ
    0.09
    ä¸Ģå¦Ĥ
    0.09
    åħ´èĩ´
    0.08
     graz
    0.08
    åĪ«è¯´
    0.08
    交æµģåIJĪä½ľ
    0.08
    _RET
    0.08
    ä¸Ģé¡¿
    0.08
    Activations Density 0.180%

    No Known Activations