© 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. 6530
    Prev
    Next
    INDEX
    Explanations

    back in time

    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
    åĪ°å¤Ħ
    -0.12
    æī°
    -0.09
    aza
    -0.09
    è¿Łè¿Ł
    -0.09
    丰ç¡ķ
    -0.09
    MeasureSpec
    -0.09
    èĿĻ
    -0.09
    _REPLY
    -0.08
    ?family
    -0.08
    eco
    -0.08
    POSITIVE LOGITS
    æŶéĹ´
    0.21
     вÑĢемени
    0.20
    æŶéĹ´åĴĮ
    0.20
    æĻĤéĸĵ
    0.19
    åħīéĺ´
    0.18
     time
    0.18
    æŶåħī
    0.18
     æŶéĹ´
    0.17
     اÙĦزÙħÙĨ
    0.17
    æĹ¶ç©º
    0.17
    Activations Density 0.047%

    No Known Activations