© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    name given or attributed

    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
    åĹij
    -0.09
    arshal
    -0.08
    izzo
    -0.08
    ниÑĨ
    -0.08
    åĭĴ
    -0.08
    åİĨåı²æĸ°
    -0.08
    æīĢæıIJä¾Ľä¹ĭ
    -0.08
    FromString
    -0.08
    ronic
    -0.08
    åı¯ä¾Ľ
    -0.08
    POSITIVE LOGITS
    称åij¼
    0.11
    没éĶĻ
    0.10
    æľ¯è¯Ń
    0.10
    说æ³ķ
    0.10
    ç¿ķ
    0.10
    ä»Ģä¹Īéĥ½
    0.09
     term
    0.09
     referring
    0.09
    çļĦ说æ³ķ
    0.09
    åIJįè¯į
    0.09
    Activations Density 0.204%

    No Known Activations