© 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. 62626
    Prev
    Next
    INDEX
    Explanations

    appears to be, clearly dangerous, may be, could 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
    çģĮ
    -0.13
    ä¸įå½±åĵį
    -0.09
    æĺ¥èĬĤæľŁéĹ´
    -0.08
     Ping
    -0.08
    åįģåŃĹ
    -0.08
     murderer
    -0.08
    èııæ³½
    -0.08
    ä¸į妨
    -0.08
    rena
    -0.08
     Mong
    -0.07
    POSITIVE LOGITS
    æĭĽ
    0.09
    æ²»å®ī
    0.09
    ëĿ¼ëıĦ
    0.09
     sez
    0.09
    å±±åĿ¡
    0.09
    خر
    0.09
    ooo
    0.08
     çe
    0.08
    åĩºåıij
    0.08
     ÙĪÙĦÙĪ
    0.08
    Activations Density 0.015%

    No Known Activations