© 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. 61678
    Prev
    Next
    INDEX
    Explanations

    internal and external relationships

    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
    岫
    -0.09
     wig
    -0.08
    ä½łè¯´
    -0.08
    沿éĢĶ
    -0.08
    é»ijçĻ½
    -0.08
    æĿĥ
    -0.08
    ALE
    -0.08
    iative
    -0.08
    人éĢł
    -0.08
    bis
    -0.08
    POSITIVE LOGITS
    åħ§éĥ¨
    0.14
    åĨħéĥ¨
    0.13
    æ»´æ»´
    0.12
    å¤ĸåľ°
    0.11
    æ°ijéĸĵ
    0.11
    è¡Įä¸ļåĨħ
    0.11
    å¤ĸéĥ¨
    0.10
    å§Ķ
    0.10
    æµģ失
    0.10
     outside
    0.10
    Activations Density 0.204%

    No Known Activations