© 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. 53563
    Prev
    Next
    INDEX
    Explanations

    all-wheel drive, 4WD, 2WD

    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
    éĹ¹
    -0.09
    ä¸ĢæĬĬ
    -0.09
    ç½ijåıĭ
    -0.09
    /hr
    -0.08
    人çĶŁ
    -0.08
     jud
    -0.08
    èĪįå¾Ĺ
    -0.08
     Drake
    -0.08
    åĽŀè´Ń
    -0.08
    raph
    -0.08
    POSITIVE LOGITS
    åģ¥
    0.11
    éĽĴ
    0.10
    è°¦
    0.10
    家ä½ı
    0.10
    Spy
    0.10
    åįłåľ°
    0.10
    FileSync
    0.09
    estre
    0.09
    erre
    0.09
    enberg
    0.09
    Activations Density 0.063%

    No Known Activations