© 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. 35897
    Prev
    Next
    INDEX
    Explanations

    words starting with h

    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
    æĸ°é²ľ
    -0.10
    æ±Łæ·®
    -0.09
    æ¼Ķ
    -0.09
    Ãłng
    -0.09
    solete
    -0.09
     Cald
    -0.09
    æŶéĹ´åĨħ
    -0.09
    ILING
    -0.09
    cular
    -0.09
    ãĥªãĥ³ãĤ°
    -0.08
    POSITIVE LOGITS
    å²
    0.09
     h
    0.08
    éĶĢ
    0.08
    pad
    0.08
     mee
    0.08
    .Raise
    0.08
     Highlander
    0.08
    åĵĨ
    0.08
    ä¸Ģæľµ
    0.08
    =h
    0.08
    Activations Density 0.039%

    No Known Activations