© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    user profile metadata

    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
    ç«¿
    -0.10
    åĵ¨
    -0.10
    REFERENCE
    -0.09
    ä¸įå®Į
    -0.08
    åıªä¸įè¿ĩæĺ¯
    -0.08
    æŃĥ
    -0.08
    å»īä»·
    -0.08
     Sponsored
    -0.08
    è§ĩ
    -0.08
    表çĻ½
    -0.08
    POSITIVE LOGITS
    /lic
    0.10
    badge
    0.09
    @brief
    0.08
     Mig
    0.08
    idable
    0.08
    家ä½ı
    0.08
    Joined
    0.08
    âľŃ
    0.08
    å¸ĤåĮº
    0.08
    _ioctl
    0.08
    Activations Density 0.017%

    No Known Activations