© 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. 21816
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    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
    ä¸Ģä½ĵ
    -0.09
    çīĪæĿĥæīĢæľī
    -0.09
    esses
    -0.09
    ught
    -0.09
    åĬŁå¤«
    -0.09
    rodu
    -0.08
    çİ©
    -0.08
    è¾ij
    -0.08
    æĸ
    -0.08
     boo
    -0.08
    POSITIVE LOGITS
    MLS
    0.09
     Seller
    0.08
    orgeous
    0.08
    被åĬ¨
    0.08
    è¥Ł
    0.08
    -runner
    0.08
    è¿Ļå¼ł
    0.07
    æ°¾
    0.07
    MB
    0.07
     quiet
    0.07
    Activations Density 0.149%

    No Known Activations