© 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. 28135
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     zwar
    -0.13
    è³´
    -0.10
    èĻ½çĦ¶
    -0.10
    èµĸ
    -0.10
    丼
    -0.10
    å¼ĢçĿĢ
    -0.09
    çģ«çĥ§
    -0.09
    èĬĴ
    -0.09
    ä½ĨæĪij
    -0.08
     although
    -0.08
    POSITIVE LOGITS
    æľīéĻIJ
    0.09
    entimes
    0.09
    limited
    0.09
    å°Ĩåħ¶
    0.08
    SED
    0.08
    PIN
    0.08
    妨
    0.08
    ICI
    0.08
    åħ·ä½ĵ
    0.08
    æ³Ĺ
    0.08
    Activations Density 0.059%

    No Known Activations