© 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. 54218
    Prev
    Next
    INDEX
    Explanations

    route segments

    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
    åī¯
    -0.12
    被çĽĹ
    -0.09
    è°ĪæģĭçĪ±
    -0.09
    è¿Ļ两ç§į
    -0.09
    _SAN
    -0.08
    _UL
    -0.08
    parator
    -0.08
    ãģĹãģ¦ãģĬãģı
    -0.08
    ulp
    -0.08
    BEST
    -0.08
    POSITIVE LOGITS
    è¡Įç¨ĭ
    0.21
    æĹħç¨ĭ
    0.15
    è·¯ç¨ĭ
    0.14
    ä¸Ģ段
    0.11
     journey
    0.11
    ç»ĪçĤ¹
    0.11
    山路
    0.11
    çݯèĬĤ
    0.11
    éĢĶ
    0.11
    路段
    0.10
    Activations Density 0.095%

    No Known Activations