© 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. 19220
    Prev
    Next
    INDEX
    Explanations

    bank account secure

    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
    éİĸ
    -0.10
    解éĶģ
    -0.10
    è¿Ŀæ³ķè¡Į为
    -0.10
    æĸ°æµªå¾®åįļ
    -0.08
    éĶģ
    -0.08
    æĮĤ
    -0.08
     unlocks
    -0.08
    Aws
    -0.08
    ç¥ĸåĽ½
    -0.08
    ipo
    -0.08
    POSITIVE LOGITS
    åķĨ
    0.11
    Disclosure
    0.10
    å®īåħ¨ä¿Ŀéļľ
    0.10
     merchants
    0.10
    订
    0.10
    ä¿¡çĶ¨åį¡
    0.09
     merchant
    0.09
    _identity
    0.09
    åķĨä¸ļéĵ¶è¡Į
    0.09
     Merchant
    0.09
    Activations Density 0.123%

    No Known Activations