© 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. 63432
    Prev
    Next
    INDEX
    Explanations

    together or with others

    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
    被åĪĹåħ¥
    -0.09
    bout
    -0.08
     conflict
    -0.08
    æijĦ
    -0.08
    åĨħ马
    -0.08
     Clo
    -0.08
    Conflict
    -0.08
    éĹ´æİ¥
    -0.08
     CONTR
    -0.08
    è´¨éĩıåĴĮ
    -0.08
    POSITIVE LOGITS
    ä¸Ģèµ·
    0.26
    åħ±åIJĮ
    0.24
     together
    0.23
    æĪij们ä¸Ģèµ·
    0.21
    ä¸Ģç·Ĵãģ«
    0.21
     вмеÑģÑĤе
    0.20
     Together
    0.19
     gemeins
    0.19
     íķ¨ê»ĺ
    0.19
    ä¸Ģèµ·åİ»
    0.18
    Activations Density 0.135%

    No Known Activations