© 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. 7864
    Prev
    Next
    INDEX
    Explanations

    subcutaneous

    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
    å¿«æĬ¥
    -0.09
    _DD
    -0.09
    ç¼´è´¹
    -0.09
    биÑĤ
    -0.08
    ãģij
    -0.08
    weeney
    -0.08
    lian
    -0.08
    éľģ
    -0.08
    åģĪ
    -0.08
    åħ´
    -0.08
    POSITIVE LOGITS
    çļ®èĤ¤
    0.12
     skin
    0.11
     Skin
    0.10
     depressing
    0.10
    çļ®
    0.10
    被æĬĵ
    0.10
     flesh
    0.09
    çĸ±
    0.09
    oulos
    0.09
     bü
    0.09
    Activations Density 0.360%

    No Known Activations