© 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. 10708
    Prev
    Next
    INDEX
    Explanations

    purpose or explanation

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    使ä¹ĭ
    -0.09
    è¿İæİ¥
    -0.09
    æŁ¬
    -0.09
    ither
    -0.08
     pal
    -0.08
    èĤ©
    -0.08
    è¿IJçĶ¨
    -0.08
     fitting
    -0.08
    妥åĸĦ
    -0.08
    POSITIVE LOGITS
    äºĨ解
    0.11
    åIJİåı°
    0.10
    çŀŃ解
    0.10
    缴è§Ĥ
    0.10
    NTAX
    0.10
    виз
    0.10
    _raise
    0.10
    åı¯ä»¥çľĭåĩº
    0.09
    çľĭåĩº
    0.09
    æĦŁè§¦
    0.09
    Activations Density 0.142%

    No Known Activations