© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    process and procedure

    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
    iping
    -0.09
    2
    -0.09
    å½ĵä¸ĭ
    -0.09
    çĶ¨éĩı
    -0.09
    å°±ä¸ļå²Ĺä½į
    -0.09
     stir
    -0.08
    èµĸ以
    -0.08
     Banc
    -0.08
    5
    -0.08
    6
    -0.08
    POSITIVE LOGITS
     process
    0.33
    è¿ĩç¨ĭ
    0.33
     пÑĢоÑĨеÑģÑģ
    0.28
    process
    0.25
    éģİç¨ĭ
    0.25
     processes
    0.25
    çļĦè¿ĩç¨ĭ
    0.24
     processo
    0.24
    è¿ĩç¨ĭä¸Ń
    0.24
     proces
    0.22
    Activations Density 0.176%

    No Known Activations