© 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. 61605
    Prev
    Next
    INDEX
    Explanations

    section or list delimiters

    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
    llib
    -0.10
    é¦ĸéĢī
    -0.09
    IVEN
    -0.09
    è¿Ļ群
    -0.09
    侯
    -0.09
    没è§ģè¿ĩ
    -0.09
    该æĿij
    -0.09
     mole
    -0.09
    é¦ĸåħĪæĺ¯
    -0.08
    æĵİ
    -0.08
    POSITIVE LOGITS
    åľ¨æľªæĿ¥
    0.09
    人åı£
    0.08
    оде
    0.08
    å¯¹æľªæĿ¥
    0.08
    å°±èĥ½å¤Ł
    0.08
    ìį¨
    0.08
    enting
    0.08
    otr
    0.08
    åľ¨æѤ
    0.08
    éĢļè¿ĩ对
    0.08
    Activations Density 0.032%

    No Known Activations