© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    rear view mirrors and blind spots

    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
    icut
    -0.10
    è¾ĵéĢģ
    -0.09
    太å¤ļäºĨ
    -0.09
     slick
    -0.09
    åı¯æĥ³
    -0.08
    HLT
    -0.08
     comp
    -0.08
     Serif
    -0.08
    裸
    -0.08
    CHASE
    -0.08
    POSITIVE LOGITS
    æŃ»è§Ĵ
    0.12
    éģĵè·¯ä¸Ĭ
    0.09
    åIJİæĤĶ
    0.09
    éķľ
    0.09
     hind
    0.09
    è¡Ĺéģĵ
    0.08
    éģĵ路交éĢļ
    0.08
    åIJİæİĴ
    0.08
     Rear
    0.08
    å®īåħ¨
    0.08
    Activations Density 0.175%

    No Known Activations