© 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. 31203
    Prev
    Next
    INDEX
    Explanations

    descriptor noun phrases

    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
    omorphic
    -0.10
    æ§ģ
    -0.09
    actively
    -0.09
    失è°ĥ
    -0.09
    imately
    -0.09
    æģ°å¥½
    -0.08
    fully
    -0.08
    ised
    -0.08
    è¾ľè´Ł
    -0.08
    æĮ¹
    -0.08
    POSITIVE LOGITS
    ness
    0.17
    NESS
    0.13
    iveness
    0.10
    eness
    0.10
     ness
    0.09
    aison
    0.09
    ivec
    0.09
    ç¨ĭ度
    0.09
    è¿ĻäºĽéĥ½æĺ¯
    0.08
    cy
    0.08
    Activations Density 0.600%

    No Known Activations