© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    still remains, occurs, has

    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
    ä»İæĿ¥æ²¡
    -0.09
     Bra
    -0.09
     Pens
    -0.09
    缮åīįå·²ç»ı
    -0.09
    ä¸ĢçĽ´æ²¡æľī
    -0.08
    岸
    -0.08
    墨
    -0.08
    _JUMP
    -0.08
    çĶ¸
    -0.08
    REW
    -0.08
    POSITIVE LOGITS
    èĮ¬
    0.09
    çIJ¦
    0.09
    ä¸ĬãģĮãĤĬ
    0.09
    _odd
    0.09
    åĪ¶çº¦
    0.09
    dle
    0.09
    Mvc
    0.09
    guarded
    0.09
    å±ł
    0.09
    æĭ³å¤´
    0.08
    Activations Density 0.036%

    No Known Activations