© 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. 31135
    Prev
    Next
    INDEX
    Explanations

    normal contexts

    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
    _requires
    -0.09
    ä¸Ģ件äºĭ
    -0.08
    ä¼ij
    -0.08
    udios
    -0.08
    çļĦéģĵçIJĨ
    -0.08
    第ä¸ĢæŶéĹ´
    -0.08
    SA
    -0.08
    vir
    -0.08
    ä»ĸ们
    -0.08
    acc
    -0.07
    POSITIVE LOGITS
    çĬ¶æĢģä¸ĭ
    0.10
    åģ¥åº·çļĦ
    0.10
     healthy
    0.10
    æĥħåĨµä¸ĭ
    0.10
    _NORMAL
    0.10
    潺
    0.09
    healthy
    0.09
    æŃ£å¸¸çļĦ
    0.09
    inne
    0.09
    人éĥ½
    0.09
    Activations Density 0.221%

    No Known Activations