© 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. 26512
    Prev
    Next
    INDEX
    Explanations

    brain waves, bio, alpha, delta, autonomics

    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
    èµ°ä¸ĭåİ»
    -0.10
    çĦ¦
    -0.10
    èĻŀ
    -0.09
    æıIJéĢŁ
    -0.09
    .annot
    -0.09
    anium
    -0.09
    ifr
    -0.09
    á»ĩp
    -0.09
    没åĬŀæ³ķ
    -0.09
    å°±æѤ
    -0.09
    POSITIVE LOGITS
    å¹³éĿĻ
    0.10
    éŀŃ
    0.10
    çĶµåĻ¨
    0.09
    çĶ«
    0.09
     badges
    0.08
    让èĩªå·±
    0.08
    æ¸ħéĨĴ
    0.08
    å³°åĢ¼
    0.08
    æĿ¾å¼Ľ
    0.08
    é¦ĸå¯Į
    0.08
    Activations Density 0.197%

    No Known Activations