© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    partnership, alliance, collaboration

    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
    æĺ¼å¤ľ
    -0.09
    mur
    -0.08
    utes
    -0.08
    оÑĩно
    -0.08
    èĴ²
    -0.08
    ocos
    -0.08
    æĤ¨çļĦåŃ©åŃIJ
    -0.08
     акÑĤÑĥ
    -0.08
    çĴĭ
    -0.08
    æī¾åĽŀ
    -0.08
    POSITIVE LOGITS
    åıĮæĸ¹
    0.14
    åIJĪä½ľåįıè®®
    0.14
    æĪĺçķ¥åIJĪä½ľ
    0.12
    çīµæīĭ
    0.10
    åIJĪä½ľåħ³ç³»
    0.10
    åįıè®®
    0.10
    å°įæĸ¹
    0.10
    对æĸ¹
    0.10
    åįıå®ļ
    0.10
    åIJĪä½ľ
    0.10
    Activations Density 0.091%

    No Known Activations