© 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. 62420
    Prev
    Next
    INDEX
    Explanations

    immutable or final states

    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
    åĸĦ
    -0.10
    åīįæīĢæľª
    -0.09
    åªļ
    -0.09
    è¿ĺä¸įæĺ¯
    -0.08
    è§Ĭ
    -0.08
     ÑĤеп
    -0.08
    æ°§æ°Ķ
    -0.08
    æĸ°è§Ħ
    -0.08
    åłĨ
    -0.08
    çIJĨ
    -0.08
    POSITIVE LOGITS
    åĽºå®ļ
    0.27
    åĽºå®ļçļĦ
    0.26
     fixed
    0.22
    ä¸įåıĺ
    0.22
    fixed
    0.20
     Fixed
    0.20
    Fixed
    0.19
    ä¸įåĬ¨
    0.19
    -fixed
    0.19
    _fixed
    0.18
    Activations Density 0.292%

    No Known Activations