© 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. 34217
    Prev
    Next
    INDEX
    Explanations

    look away, turn, gaze

    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
    éķľ
    -0.09
    åħľ
    -0.09
    åī§ç»Ħ
    -0.09
    دÙĪ
    -0.08
    ç¼ł
    -0.08
    è·ĭ
    -0.08
    åĵģ
    -0.08
    iras
    -0.08
     hopes
    -0.08
     Cle
    -0.08
    POSITIVE LOGITS
    åĽŀéģ¿
    0.09
    Away
    0.09
    ä¸ĭçıŃ
    0.09
    åĤ¬
    0.09
    egov
    0.09
    èĴĻ
    0.09
    .Net
    0.08
    è§Ĩ线
    0.08
    ä¸įå¿į
    0.08
    éĢģè´§
    0.08
    Activations Density 0.019%

    No Known Activations