© 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. 18478
    Prev
    Next
    INDEX
    Explanations

    ply and plywood constructions

    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
    åŁł
    -0.09
    çªĿ
    -0.09
    æ¶Ķ
    -0.09
    æłĢ
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    éħ·
    -0.09
    izedName
    -0.09
    æ£ķèī²
    -0.09
    éĢ¦
    -0.09
    æijĪ
    -0.09
    POSITIVE LOGITS
    matic
    0.10
    soc
    0.10
    elin
    0.09
    inator
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    man
    0.09
    ments
    0.09
    ç¯ģ
    0.08
    gun
    0.08
    sig
    0.08
    Activations Density 0.009%

    No Known Activations