© 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. 61220
    Prev
    Next
    INDEX
    Explanations

    PCC

    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
    _UTIL
    -0.09
    IFICATIONS
    -0.09
    ðŁ¥º
    -0.09
    塬
    -0.09
    FINITY
    -0.09
    emarks
    -0.08
    _BOUND
    -0.08
    setData
    -0.08
     LSB
    -0.08
    赶
    -0.08
    POSITIVE LOGITS
    ç®Ģ称
    0.24
    åıĪ称
    0.13
     aka
    0.13
    ä¿Ĺ称
    0.13
    以ä¸ĭç®Ģ称
    0.12
     abbreviated
    0.11
    aka
    0.11
    ä¹Łå°±æĺ¯
    0.10
    ä¸ĭ称
    0.10
    缩
    0.10
    Activations Density 0.399%

    No Known Activations