© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22148
    Prev
    Next
    INDEX
    Explanations

    bring something

    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
    çīµ
    -0.12
    auce
    -0.10
    çīµå¼ķ
    -0.09
    çī½
    -0.09
    åĴ½åĸī
    -0.09
    æĶ¾è¿ĩ
    -0.08
    éĺĤ
    -0.08
    дÑĥÑĤ
    -0.08
    enko
    -0.08
    hung
    -0.08
    POSITIVE LOGITS
     ׾×Ļ×ĵ×Ļ
    0.15
    ToFront
    0.14
    带åĪ°
    0.12
    åħ³æ³¨åº¦
    0.10
    è¿ĽæĿ¥
    0.10
    带æĿ¥
    0.10
    ä¸Ģèµ·
    0.09
     Bring
    0.09
    æĪij们ä¸Ģèµ·
    0.09
     bring
    0.09
    Activations Density 0.098%

    No Known Activations