© 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. 49360
    Prev
    Next
    INDEX
    Explanations

    will be

    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¡
    -0.10
    ä¸į容æĺĵ
    -0.10
    LLU
    -0.09
     Ñģвоим
    -0.09
    åİĨåı²æĤłä¹ħ
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.08
    çĭŃ
    -0.08
    ç©¿
    -0.08
    ä¸įæĺĵ
    -0.08
     Ansi
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥çľĭåĪ°
    0.09
    ä¸Ģä½ĵ
    0.08
    çŃīåĢĻ
    0.08
    opping
    0.08
    çŃīå¾ħ
    0.08
    åľ¨åºĬä¸Ĭ
    0.08
     patt
    0.08
    鼾
    0.08
    ä¿¡æģ¯åıijå¸ĥ
    0.08
    abox
    0.08
    Activations Density 0.028%

    No Known Activations