© 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. 5912
    Prev
    Next
    INDEX
    Explanations

    Avatar, elements, fire, earth

    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
    天èĬ±
    -0.09
    ä¸Ģéģĵ
    -0.09
    çªŁ
    -0.09
    åķĨ家
    -0.09
    =Value
    -0.09
    èĥİ
    -0.09
    æŀķ
    -0.09
    çħ§
    -0.09
    .jd
    -0.09
    onis
    -0.09
    POSITIVE LOGITS
    å°Ķæĸ¯
    0.10
    åĽŀäºĭ
    0.10
     elements
    0.09
    éĵĤ
    0.09
    elements
    0.09
    åħĥç´ł
    0.09
    ائÙĬ
    0.09
    çģŃçģ«
    0.09
    æ»Ķ
    0.09
    çŁ¿çī©è´¨
    0.09
    Activations Density 0.043%

    No Known Activations