© 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. 32700
    Prev
    Next
    INDEX
    Explanations

    word trick

    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
    hibit
    -0.10
    hip
    -0.10
    æѤåĪ»
    -0.10
    éĻħ
    -0.09
    æ¡£
    -0.09
    ocking
    -0.09
    ä¸Ģçīĩ
    -0.09
    å¾Ĺèµ·
    -0.09
    bras
    -0.09
    åľ°ä¸Ńæµ·
    -0.09
    POSITIVE LOGITS
    iest
    0.11
    ery
    0.11
    iness
    0.10
    åĦ¿
    0.10
    å¤ļå¤ļ
    0.10
    è¦ģ害
    0.09
    ened
    0.08
    itt
    0.08
    ../../../
    0.08
    omatic
    0.08
    Activations Density 0.007%

    No Known Activations