© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50938
    Prev
    Next
    INDEX
    Explanations

    license. synthesis. changes. matrix multiplication. questions. arrays. systems. bug killer. directory. exported logger

    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
    ä¸įæŃ»
    -0.08
    بغ
    -0.08
    Spo
    -0.08
    ä¸įä¹ħ
    -0.08
    æħİ
    -0.08
     ttl
    -0.08
    ä¸įä¸ĭ
    -0.07
    dao
    -0.07
    boom
    -0.07
    éī´
    -0.07
    POSITIVE LOGITS
     Cumberland
    0.10
    омеÑĢ
    0.09
    çĴł
    0.09
    åı¦ä¸Ģè¾¹
    0.09
    çĿ¬
    0.09
     ÐŁÑĢе
    0.09
     Affero
    0.08
    ä½ĵä¼ļ
    0.08
    æIJĤ
    0.08
    åı¦ä¸Ģä½į
    0.08
    Activations Density 0.991%

    No Known Activations