© 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. 63687
    Prev
    Next
    INDEX
    Explanations

    capable pilots, reliable narrator

    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
    æī¹è¯Ħ
    -0.09
     traps
    -0.09
    ptest
    -0.08
    åĮ¿åIJį
    -0.08
    è°
    -0.08
    æ¶Ī
    -0.08
    utor
    -0.08
    åѦçĶŁä»¬
    -0.08
    prot
    -0.08
     Trap
    -0.08
    POSITIVE LOGITS
    åı¯éĿł
    0.19
    åı¯éĿłæĢ§
    0.18
     reliability
    0.15
    ç´łè´¨
    0.14
    åı¯éĿłçļĦ
    0.14
    åı¯ä¿¡
    0.14
    ä¸įåħ·å¤ĩ
    0.14
    åĵģæł¼
    0.12
     unreliable
    0.12
    ä¿¡èªī
    0.12
    Activations Density 0.088%

    No Known Activations