© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    data transmission

    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
    æ°Ĺãģ«ãģªãĤĭ
    -0.08
    宾客
    -0.08
    _SDK
    -0.08
    éĹ»
    -0.08
    .inputs
    -0.08
     Narc
    -0.08
    çłĸ
    -0.08
    çıĬçijļ
    -0.08
    contr
    -0.07
    çľĭ书
    -0.07
    POSITIVE LOGITS
    ä¼łè¾ĵ
    0.14
    ä¼łéĢģ
    0.13
    ä¼łéĢĴ
    0.12
    ç©¿è¿ĩ
    0.10
    æīģ
    0.10
    æĮŁ
    0.10
    è·¨è¶Ĭ
    0.10
    æī¿è½½
    0.09
    è¿Ľåĩº
    0.09
    åĩŃè¯ģ
    0.09
    Activations Density 0.270%

    No Known Activations