© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20859
    Prev
    Next
    INDEX
    Explanations

    metals and materials

    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
    æ²»çĹħ
    -0.10
    åľ¨äº¬
    -0.09
    asan
    -0.09
    åĽ½æľīèµĦ产
    -0.09
    ponce
    -0.09
     Ground
    -0.09
    èĦ±ç¦»
    -0.09
    ucid
    -0.09
    isen
    -0.09
    ona
    -0.08
    POSITIVE LOGITS
    éĢī举
    0.09
    涯
    0.08
     everlasting
    0.08
    USAGE
    0.08
     Polo
    0.08
    subst
    0.08
     brows
    0.08
    åī¡
    0.08
    uls
    0.08
    extract
    0.08
    Activations Density 0.007%

    No Known Activations