© 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. 5227
    Prev
    Next
    INDEX
    Explanations

    bolts and screws

    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
    isman
    -0.11
    æĹłç©·
    -0.10
    çIJ¼
    -0.09
    arma
    -0.09
    iral
    -0.09
    è°Ĩ
    -0.09
    æ·±è¿ľ
    -0.08
    éĻĢ
    -0.08
    主ä¹īèĢħ
    -0.08
    atem
    -0.08
    POSITIVE LOGITS
    æĻ®
    0.09
    deen
    0.08
    ç½ij绾å®īåħ¨
    0.08
    пло
    0.08
    çĽĺçĤ¹
    0.08
    é¸Ń
    0.08
    birds
    0.08
     Scalars
    0.08
    éĺµå®¹
    0.08
    shirt
    0.08
    Activations Density 0.032%

    No Known Activations