© 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. 8874
    Prev
    Next
    INDEX
    Explanations

    qualitatively and quantitatively

    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
    æŁ¯
    -0.10
    ä¸ĭåij¨
    -0.09
    rum
    -0.09
    lov
    -0.09
    _configure
    -0.08
    ASI
    -0.08
    ä¸Ģè·¯ä¸Ĭ
    -0.08
    ä¸įæŃ¢
    -0.08
    opcode
    -0.08
    lops
    -0.08
    POSITIVE LOGITS
    å®ļéĩı
    0.11
    èįīåľ°
    0.10
    itative
    0.09
    URED
    0.09
    æ·±åĪ»çļĦ
    0.09
    aug
    0.08
    åĦ¿å¥³
    0.08
     qualitative
    0.08
    转æĬĺ
    0.08
    èįī
    0.08
    Activations Density 0.080%

    No Known Activations