© 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. 55494
    Prev
    Next
    INDEX
    Explanations

    pituitary function/response/axis

    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
    å¼ĢéĺĶ
    -0.10
    adr
    -0.10
    åħĭæľį
    -0.09
    è´¢å¯Į
    -0.09
    ä¸į让
    -0.09
    æ¢Ĺ
    -0.09
    é²ł
    -0.09
    ä¼ĺèī¯
    -0.09
    æī¶
    -0.08
    è£Ļ
    -0.08
    POSITIVE LOGITS
    æ´½
    0.10
    åĪĨæ³Į
    0.09
    _DT
    0.09
    主管
    0.09
    æŃ¤é¡¹
    0.09
    æ²»
    0.09
    gran
    0.08
    éĿ¢å®¹
    0.08
    è¿IJ转
    0.08
    éŀį
    0.08
    Activations Density 0.258%

    No Known Activations