© 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. 21693
    Prev
    Next
    INDEX
    Explanations

    those who

    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
    ozy
    -0.08
    ç¥ĩ
    -0.08
    ä¸ĢæīĢ
    -0.08
    ä¸Ģ个好çļĦ
    -0.08
    çªį
    -0.08
    赡
    -0.08
    è¾ľè´Ł
    -0.07
    å±ĭéĩĮ
    -0.07
    Town
    -0.07
    ä¸Ģ头
    -0.07
    POSITIVE LOGITS
    çĨŁæĤī
    0.16
    æľīåħ´è¶£
    0.14
    éĤ£äºĽ
    0.14
    çļĦ人éĥ½
    0.14
    æĦŁåħ´è¶£
    0.12
    èĢħ
    0.12
    Anyone
    0.12
     anyone
    0.12
    Those
    0.12
     Anyone
    0.12
    Activations Density 0.075%

    No Known Activations