© 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. 23422
    Prev
    Next
    INDEX
    Explanations

    posting something

    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
    åijĬè¯ī她
    -0.09
    åı¯èĥ½åĩºçİ°
    -0.09
    itol
    -0.09
    soever
    -0.09
    åģľæĶ¾
    -0.09
    人身
    -0.08
     Dexter
    -0.08
    å¾Ģ
    -0.08
    å¥Ī
    -0.08
    çķĻåľ¨
    -0.08
    POSITIVE LOGITS
    åħ³äºİ
    0.10
     about
    0.10
    pone
    0.10
     vá»ģ
    0.09
     tentang
    0.09
    _advance
    0.09
    éĹľæĸ¼
    0.09
    _ENC
    0.09
    ocl
    0.08
    ä¸ĵéĹ¨ä¸º
    0.08
    Activations Density 0.023%

    No Known Activations