© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38359
    Prev
    Next
    INDEX
    Explanations

    StringValue

    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
    çīł
    -0.11
    ç®Ķ
    -0.10
    å®ĥçļĦ
    -0.09
    æİ¥è¿ij
    -0.09
    nod
    -0.09
    çĴľ
    -0.09
    大家åĪĨ享
    -0.09
    odal
    -0.09
    é«ĺå°Ķ
    -0.09
    æ·±åħ¥
    -0.08
    POSITIVE LOGITS
    继
    0.08
    æĢ¡
    0.08
    _mm
    0.08
    顽
    0.07
    åİĨåı²æĸ°
    0.07
    ãģ¤ãģĦ
    0.07
    æĦı大
    0.07
    emean
    0.07
    åıĹ害
    0.07
    StringValue
    0.07
    Activations Density 0.141%

    No Known Activations