© 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. 38337
    Prev
    Next
    INDEX
    Explanations

    is part of

    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¸Ģ个éĩįè¦ģ
    -0.12
    æĺ¯ä¸Ģ项
    -0.11
     cầm
    -0.10
    åĽłä¸ºå¥¹
    -0.10
    éľĨ
    -0.10
    åĻ¨åħ·
    -0.10
    åİŁåĽłä¹ĭä¸Ģ
    -0.10
    æģ°å½ĵ
    -0.09
    åİĺ
    -0.09
    éĩIJ
    -0.09
    POSITIVE LOGITS
    pired
    0.10
    UCH
    0.09
    alg
    0.09
    åľ¨è¿Ļç§į
    0.09
    коÑģ
    0.08
    atism
    0.08
    anter
    0.08
    ç³»
    0.08
     PURE
    0.08
    bish
    0.08
    Activations Density 0.121%

    No Known Activations