© 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. 32433
    Prev
    Next
    INDEX
    Explanations

    describing events or states

    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
     Frag
    -0.08
     fragile
    -0.07
    /or
    -0.07
    hy
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    å°ıç¼ĸ
    -0.07
     Pan
    -0.07
    berman
    -0.07
     Pin
    -0.06
    ä¹Łå°±æĺ¯
    -0.06
    POSITIVE LOGITS
     دÙħØ´
    0.11
    åľ°æłĩ
    0.11
    æĥħåĨµè¿Ľè¡Į
    0.11
    åķĨä¸ļåĮĸ
    0.10
    大å®Ĺ
    0.10
    åįĸæİī
    0.10
    ofday
    0.10
     pornost
    0.10
    åıijå±ķ空éĹ´
    0.10
    empor
    0.10
    Activations Density 1.482%

    No Known Activations