© 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. 49158
    Prev
    Next
    INDEX
    Explanations

    telephone parts and functions

    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¸į代表
    -0.11
    ldata
    -0.09
    åŃĿ
    -0.09
    纷
    -0.09
    trak
    -0.09
    æīĵåĩº
    -0.08
    åĨ²
    -0.08
    趾
    -0.08
     Conf
    -0.08
    åĨ²æ´Ĺ
    -0.08
    POSITIVE LOGITS
    æĶ¾å¤§
    0.11
    çĶµè¯Ŀ
    0.11
    æī©
    0.11
    ä¸Ģéĥ¨
    0.10
    telephone
    0.10
     telephone
    0.10
    åIJ¯èĴĻ
    0.10
    è¡į
    0.10
    èĪ£
    0.09
    PIP
    0.09
    Activations Density 0.109%

    No Known Activations