© 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. 27659
    Prev
    Next
    INDEX
    Explanations

    transcription factors

    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
    ãĤ¿ãĤ¤
    -0.10
    çĥŃ度
    -0.08
    VAS
    -0.08
    éĻĤ
    -0.08
    éļIJ身
    -0.08
     boca
    -0.08
    å¤ĸæĿ¥
    -0.08
     Disco
    -0.08
    quil
    -0.07
    Ùĥرة
    -0.07
    POSITIVE LOGITS
    室
    0.12
    å¢ĥ
    0.10
    æ»
    0.09
    lew
    0.09
     заÑĤ
    0.09
    åĽŀæĬ¥
    0.09
    æ·¡æ°´
    0.09
    æ£Ĥ
    0.09
    室åĨħ
    0.09
    æĭĽåĭŁ
    0.09
    Activations Density 0.289%

    No Known Activations