© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    cropping season

    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
    è¡Įä¸ļçļĦ
    -0.11
    éħ¬
    -0.10
    /Branch
    -0.09
    Industry
    -0.09
    orest
    -0.09
    éľĩ
    -0.09
    ãģĤãģ¨
    -0.09
     Industry
    -0.09
    åļĩ
    -0.09
    è¡Įä¸ļä¸Ń
    -0.09
    POSITIVE LOGITS
    çĶŁäº§åĬĽ
    0.09
    åħ±äº§
    0.09
    æĸ½
    0.09
    è§ĦåĪĴ设计
    0.08
    æ··
    0.08
    éķ¿è¿ľ
    0.08
     Tol
    0.08
     Pol
    0.08
    竺
    0.08
    åħ±åIJĮåıijå±ķ
    0.08
    Activations Density 0.080%

    No Known Activations