© 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. 35182
    Prev
    Next
    INDEX
    Explanations

    called, dubbed, considered

    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
    åŃĺéĩı
    -0.11
    rew
    -0.11
    Falsy
    -0.10
    çIJ
    -0.10
    togroup
    -0.10
    (EXPR
    -0.10
     tÃŃch
    -0.10
    REW
    -0.09
    åĬłåĪĨ
    -0.09
    æijĦ
    -0.09
    POSITIVE LOGITS
    æĺ¯åĽ½åĨħ
    0.10
    æĺ¯éŁ©åĽ½
    0.09
    å¡«è¡¥
    0.09
    ç»
    0.09
    说è¿ĩ
    0.08
    åĨħéĻĨ
    0.08
    æĺ¯ä¸Ģ项
    0.08
    “
    0.08
    ature
    0.07
    æī¾åĩĨ
    0.07
    Activations Density 0.053%

    No Known Activations