© 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. 49515
    Prev
    Next
    INDEX
    Explanations

    output or result

    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°´æºIJ
    -0.08
    è¿Ļæł·åģļ
    -0.08
    0
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
    çŃīåĽłç´ł
    -0.08
    ä¼ļ使
    -0.08
    ä»Ģä¹ĪåİŁåĽł
    -0.08
    -established
    -0.08
    åĬ³
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    è¾ĵåĩº
    0.16
     output
    0.15
    =output
    0.14
    ç»ĵæŀľ
    0.13
    output
    0.13
     ê²°ê³¼
    0.13
    (output
    0.13
    _ready
    0.12
     ì¶ľëł¥
    0.12
     è¾ĵåĩº
    0.12
    Activations Density 0.685%

    No Known Activations