© 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. 2901
    Prev
    Next
    INDEX
    Explanations

    and followed by conjunctions or common verbs

    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
    .cos
    -0.09
    åıĹ
    -0.09
    åı£
    -0.08
    ãģªãģijãĤĮãģ°
    -0.08
    ALER
    -0.08
    erville
    -0.08
    è¿ĺè¦ģ
    -0.08
    awa
    -0.08
    .ce
    -0.08
    æĻ¤
    -0.08
    POSITIVE LOGITS
    åĽłæѤ
    0.10
    åĽłèĢĮ
    0.10
    ä¹ĭç¾İ
    0.09
    æīĢä»¥åľ¨
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
     Madness
    0.09
    ä½Ĩä¹Ł
    0.09
    产åĢ¼
    0.09
    èĢĮåİ»
    0.09
     nên
    0.08
    Activations Density 0.320%

    No Known Activations