© 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. 54148
    Prev
    Next
    INDEX
    Explanations

    numbers followed by or related to distance/paths

    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
    åŀĤ
    -0.09
    ounge
    -0.09
     kl
    -0.09
    çĶµåĻ¨
    -0.08
    ColumnInfo
    -0.08
    çĶµçº¿
    -0.08
    OOT
    -0.08
    VEL
    -0.08
    _INST
    -0.08
    .sy
    -0.08
    POSITIVE LOGITS
    -dist
    0.10
    æ·«
    0.09
    ç§ģèIJ¥
    0.09
    /dist
    0.09
    è·¯ä¸Ĭ
    0.09
    羣çĪ±
    0.09
    ç¬Ļ
    0.09
    罨
    0.09
    è¿ĻæĿ¡è·¯
    0.09
    沿çĿĢ
    0.08
    Activations Density 0.044%

    No Known Activations