© 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. 27156
    Prev
    Next
    INDEX
    Explanations

    reason for, behind, that

    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
    è·Łä»ĸ
    -0.09
    weed
    -0.09
    راÙĩ
    -0.09
    stones
    -0.09
    èķ¾
    -0.08
    ÙĨÙĪ
    -0.08
    èĻ±
    -0.08
    èŁ²
    -0.08
    eing
    -0.08
     Indies
    -0.08
    POSITIVE LOGITS
    nable
    0.11
    ably
    0.11
    人们对
    0.11
    nement
    0.10
    nel
    0.10
    庵
    0.09
    rup
    0.09
    ëĮĢë¡ľ
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
    ãģªãģı
    0.09
    Activations Density 0.040%

    No Known Activations