© 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. 22879
    Prev
    Next
    INDEX
    Explanations

    brave or crazy

    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
    æīĭä¸ĭ
    -0.09
    assing
    -0.08
    allet
    -0.08
    ä¸Ńåľº
    -0.08
    åı¯æĥľ
    -0.08
    craft
    -0.08
    尽快
    -0.08
    è¡Ķ
    -0.08
    ãĤ¶ãĥ¼
    -0.08
    ç¿Ķ
    -0.08
    POSITIVE LOGITS
    èĥĨ
    0.16
    åĨĴçĿĢ
    0.14
    éĢĨè¡Į
    0.13
    ä¸įæĢķ
    0.12
    èĢIJ
    0.12
    èĨ½
    0.12
    åĭĩæ°Ķ
    0.12
    åĨĴéĻ©
    0.12
    çĪ±å¥½
    0.12
    éĢĨ
    0.11
    Activations Density 0.079%

    No Known Activations