© 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. 26560
    Prev
    Next
    INDEX
    Explanations

    e-book, Net, Starr, cluster

    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
    apas
    -0.11
    Ont
    -0.10
    çģĮ
    -0.10
    \Object
    -0.09
    åĬĽåº¦
    -0.09
    zelf
    -0.09
     Ont
    -0.09
    ocs
    -0.09
     ont
    -0.09
    ares
    -0.08
    POSITIVE LOGITS
    æĸ¯é¡¿
    0.11
    æļ¾
    0.10
    æĻĵå¾Ĺ
    0.09
    åĽ½åľŁ
    0.09
    被æ·ĺæ±°
    0.09
    被æīĵ
    0.09
    å½Ģ
    0.09
    iben
    0.09
    ä¸Ńå±±
    0.08
    ç¥ĵ
    0.08
    Activations Density 0.071%

    No Known Activations