© 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. 61230
    Prev
    Next
    INDEX
    Explanations

    cause or responsibility

    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
    guards
    -0.08
    åIJ¬è¿ĩ
    -0.08
    åıĸæ¶Ī
    -0.08
    海峡
    -0.08
    ä½ŀ
    -0.08
    anc
    -0.08
    ä¸Ģ声
    -0.08
    /embed
    -0.08
    PTS
    -0.07
    ovich
    -0.07
    POSITIVE LOGITS
    èĥĮåIJİ
    0.15
    å¹ķåIJİ
    0.13
     behind
    0.11
     Behind
    0.11
    åĬŁåĬ³
    0.11
    æĢĢéĩĮ
    0.11
    çļĦèĥĮåIJİ
    0.10
    ponsible
    0.10
    æĿ°
    0.10
    èĥĮåIJİçļĦ
    0.09
    Activations Density 0.064%

    No Known Activations