© 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. 19195
    Prev
    Next
    INDEX
    Explanations

    turn into, turn up, turn me, turn out

    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
    план
    -0.10
    oplan
    -0.09
    åħ¶ä»ĸ人
    -0.09
    _GP
    -0.08
     ÑĢан
    -0.08
     Newman
    -0.08
    åħ¨åijĺ
    -0.08
    è´´è¿ij
    -0.08
     план
    -0.08
    PLAN
    -0.08
    POSITIVE LOGITS
    åĿıäºĭ
    0.11
    aled
    0.09
    æ±Ĥå©ļ
    0.09
     Flip
    0.08
     pä
    0.08
    éĢĴ交
    0.08
    主ä¹ī
    0.08
    flip
    0.08
     Conserv
    0.08
     flip
    0.08
    Activations Density 0.024%

    No Known Activations