© 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. 33283
    Prev
    Next
    INDEX
    Explanations

    let go or fading

    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
    åĬ±å¿Ĺ
    -0.09
    åħħåĪĨ
    -0.09
    æĽ´é«ĺ
    -0.09
    ä¸Ĭåı¸
    -0.09
    ç¬Ļ
    -0.09
    ä»İæĿ¥ä¸į
    -0.09
    Upgrade
    -0.09
    æĦļ
    -0.09
    åī¯
    -0.09
    ãģŀ
    -0.08
    POSITIVE LOGITS
    è¡°
    0.16
    失åİ»
    0.14
    è¡°éĢĢ
    0.13
    失åİ»äºĨ
    0.13
    åĢ¦
    0.12
    æĩĪ
    0.12
    èIJİ
    0.11
    失èIJ½
    0.11
    失æķĪ
    0.11
    迷失
    0.11
    Activations Density 0.134%

    No Known Activations