© 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. 11681
    Prev
    Next
    INDEX
    Explanations

    in the sights / on target

    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
    说起
    -0.11
    legacy
    -0.10
    çļĦåĬªåĬĽ
    -0.09
    çļĦåĬ¨åĬĽ
    -0.09
     Bunny
    -0.09
     hak
    -0.09
    åĪĨæķ£
    -0.09
    onas
    -0.09
    绵
    -0.09
    _CONN
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħ
    0.12
    è¿ľæĸ¹
    0.11
    éķ¿è¿ľ
    0.10
    æŁIJä¸Ģ
    0.09
    éķĿ
    0.09
    缮æłĩ
    0.09
    身æĹģ
    0.08
    Ùĥب
    0.08
    ä¸įè¿ľå¤Ħ
    0.08
    eye
    0.08
    Activations Density 0.017%

    No Known Activations