© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    must find/eat/fight/check/travel/return/make/figure

    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
    æľ
    -0.09
     pil
    -0.08
     funnel
    -0.08
    ATO
    -0.08
    ç´¯äºĨ
    -0.08
     Stub
    -0.08
    称
    -0.08
    _initializer
    -0.08
     cheat
    -0.08
    bury
    -0.08
    POSITIVE LOGITS
    帮å¿Ļ
    0.12
    å¹ħ度
    0.11
    åĽŀçŃĶ
    0.11
    éħįä¸Ĭ
    0.10
    äº§åľ°
    0.10
    çļĦå°±æĺ¯
    0.10
    éĥ¨åī¯éĥ¨éķ¿
    0.09
    帮
    0.09
    æĬĵç´§
    0.09
    á»ģn
    0.09
    Activations Density 0.086%

    No Known Activations