© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    the other way around or vice versa

    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
    elijk
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    ocre
    -0.09
    å¤ļæł·åĮĸ
    -0.09
    axis
    -0.08
    vac
    -0.08
    Vac
    -0.08
    è§Ĥ念
    -0.08
    .rc
    -0.08
    æķ¦çħĮ
    -0.08
    POSITIVE LOGITS
    ç¼Ģ
    0.11
    IEW
    0.09
    gom
    0.09
    _THAN
    0.09
    åij
    0.08
    ptune
    0.08
    为主
    0.08
     vice
    0.08
    æīįæĺ¯
    0.08
    è¾ŀ
    0.08
    Activations Density 0.024%

    No Known Activations