© 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. 62748
    Prev
    Next
    INDEX
    Explanations

    transplantation, graft, transfer

    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
     Salvador
    -0.09
     باÙĦÙħ
    -0.09
    gent
    -0.08
    å¾Ĺèµ·
    -0.08
    æĢł
    -0.08
    izedName
    -0.08
    å¸Ńåį·
    -0.08
    ÐĿÐķ
    -0.08
    ä¸ĢéĿ¢
    -0.08
    prof
    -0.08
    POSITIVE LOGITS
    _TRANSFER
    0.13
    转移
    0.13
    æĭ¼
    0.12
    onto
    0.12
    移æ¤į
    0.12
     transfer
    0.12
    Transfer
    0.11
    .Transfer
    0.11
     Transfer
    0.11
     transferred
    0.11
    Activations Density 0.420%

    No Known Activations