© 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. 32768
    Prev
    Next
    INDEX
    Explanations

    though or while contrasting clauses

    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
     zwar
    -0.15
    åĽºçĦ¶
    -0.12
    ä¸įä½Ĩ
    -0.12
    ãģĿãģĹãģ¦
    -0.11
    èĻ½
    -0.10
     конеÑĩно
    -0.09
    äºİæĺ¯
    -0.09
    æŀľçĦ¶
    -0.09
    èĻ½çĦ¶
    -0.09
    oretical
    -0.09
    POSITIVE LOGITS
     ë¶Ī구íķĺê³ł
    0.13
    åį´æĺ¯
    0.11
    æľīä¸įå°ij
    0.10
    åIJĦèĩªçļĦ
    0.10
    ä»įæľī
    0.10
    åħ¶ä½Ļ
    0.10
    æľīæīĢä¸įåIJĮ
    0.09
    jab
    0.09
    åį»
    0.09
    å®ŀéĻħæĥħåĨµ
    0.09
    Activations Density 0.059%

    No Known Activations