© 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. 11683
    Prev
    Next
    INDEX
    Explanations

    Oh yes

    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
    æĥłæ°ij
    -0.10
    ạ
    -0.09
    åĴ»
    -0.09
    çªĴæģ¯
    -0.09
    æķĪçĽĬ
    -0.09
    çĭĢ
    -0.09
    åij¼
    -0.09
    ãĥ©ãĤ¤ãĥĪ
    -0.08
    itted
    -0.08
    é»İæĺİ
    -0.08
    POSITIVE LOGITS
    çľĭè¿ĩ
    0.09
    æĹłæīĢ
    0.08
    æĬĬèĩªå·±
    0.08
    ä½łçľĭ
    0.08
     Ãĸn
    0.08
     Surrey
    0.08
     retract
    0.08
    èĥ½æĬĬ
    0.08
    antee
    0.07
     Murder
    0.07
    Activations Density 0.026%

    No Known Activations