© 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. 36134
    Prev
    Next
    INDEX
    Explanations

    authentication solution or mechanism

    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
    éħ¶
    -0.10
    UNDLE
    -0.09
    åѤåįķ
    -0.09
    çģ«èĬ±
    -0.09
    被æīĵ
    -0.09
    SED
    -0.09
    åijĬè¯ī她
    -0.09
    éķĴ
    -0.08
    alta
    -0.08
    .nom
    -0.08
    POSITIVE LOGITS
    åıįåĢĴ
    0.10
    ä¸ĬéŨ
    0.09
    åģ¥åħ¨
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    ä»»
    0.09
    _Reset
    0.09
    空æ°Ķ
    0.08
     drv
    0.08
     Pam
    0.08
    drv
    0.08
    Activations Density 0.114%

    No Known Activations