© 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. 32133
    Prev
    Next
    INDEX
    Explanations

    handedness

    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
    段
    -0.09
    æĽ¹
    -0.09
    ippet
    -0.09
    åıĸè¯ģ
    -0.08
    ä¸ĭåİ»
    -0.08
    Ju
    -0.08
    ä¸ºæľŁ
    -0.08
    绳
    -0.08
    ogo
    -0.08
    æĿŃ
    -0.08
    POSITIVE LOGITS
    åı³æīĭ
    0.15
    å·¦æīĭ
    0.14
     handed
    0.12
    -handed
    0.11
    æĬ±
    0.10
    åı³
    0.10
    /left
    0.09
    èŀºæĹĭ
    0.09
    æĭĩæĮĩ
    0.09
    èŀº
    0.09
    Activations Density 0.137%

    No Known Activations