© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38134
    Prev
    Next
    INDEX
    Explanations

    password hashing and salting

    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
    IRQ
    -0.09
    ç¢İ
    -0.09
    é¢IJ
    -0.09
     Honour
    -0.08
     IRQ
    -0.08
    尽头
    -0.08
    _navigation
    -0.08
    å¼Ĥ
    -0.08
    è¾Ĺ转
    -0.08
    Wnd
    -0.08
    POSITIVE LOGITS
     tast
    0.10
    apache
    0.09
    uzzi
    0.09
    éĩijæ²Ļ
    0.09
     sting
    0.09
    åħ¥åºĵ
    0.08
    åºĵ
    0.08
    PHA
    0.08
    çĶ·å¥³
    0.08
    ç«Ļéķ¿
    0.08
    Activations Density 0.234%

    No Known Activations