© 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. 6790
    Prev
    Next
    INDEX
    Explanations

    print statements

    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
    OrNull
    -0.11
    /from
    -0.11
    æĪijçĽ¸ä¿¡
    -0.10
    沿
    -0.09
    ãģĦãģĭ
    -0.09
    ãĤŃãĥ³
    -0.09
    åĨ¶
    -0.08
     Bans
    -0.08
    è´¨éĩıåĴĮ
    -0.08
    åĽĽå¤Ħ
    -0.08
    POSITIVE LOGITS
    ä»ĸæĺ¯
    0.11
    agraph
    0.09
    ober
    0.09
    她æĺ¯
    0.09
    _PAYLOAD
    0.09
    è¢į
    0.08
    æ¦Ķ
    0.08
    lide
    0.08
    aska
    0.08
    -tm
    0.08
    Activations Density 0.917%

    No Known Activations