© 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. 56279
    Prev
    Next
    INDEX
    Explanations

    identity theft and security

    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
    ä¿¡æģ¯å®īåħ¨
    -0.09
    åĽ½å®¶å®īåħ¨
    -0.09
    ACY
    -0.09
    è°Ĺ
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    çĻ½è¡£
    -0.08
     Safety
    -0.08
     safety
    -0.08
    edException
    -0.08
    å®īåħ¨ç®¡çIJĨ
    -0.08
    POSITIVE LOGITS
    åĬ£
    0.10
     Friedman
    0.09
    çħ²
    0.09
    rette
    0.09
    iaux
    0.09
    /sdk
    0.09
    éĢ»
    0.09
    黼
    0.09
     Grinder
    0.09
    fat
    0.09
    Activations Density 0.071%

    No Known Activations