© 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. 2079
    Prev
    Next
    INDEX
    Explanations

    confused by or about something

    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
    æ±
    -0.09
    /respond
    -0.09
    ContextHolder
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    ıt
    -0.08
    ç²¾ç¥ŀ
    -0.08
     trì
    -0.08
    manship
    -0.08
    ipes
    -0.08
    夫
    -0.08
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.15
    è§ĨåIJ¬
    0.11
    ä¸į解
    0.11
    HostException
    0.10
    ément
    0.10
    engers
    0.10
    åĴĮæĶ¯æĮģ
    0.09
    RICT
    0.09
    è¨ĢãģĪãģ°
    0.09
    atics
    0.09
    Activations Density 0.018%

    No Known Activations