© 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. 51606
    Prev
    Next
    INDEX
    Explanations

    in fact

    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
    æĢ»èĢĮè¨Ģä¹ĭ
    -0.09
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    iamond
    -0.09
    ãģ¨ãģ«ãģĭãģı
    -0.09
    otto
    -0.09
    åŃĢ
    -0.09
    çħ§
    -0.09
    æĸ¯é¡¿
    -0.09
    æĮ¹
    -0.08
    ensity
    -0.08
    POSITIVE LOGITS
    ored
    0.11
    rec
    0.09
    èĮļ
    0.09
    ëĮĢë¡ľ
    0.09
    edList
    0.08
    /address
    0.08
    饶
    0.08
    è¾°
    0.08
    alled
    0.08
     Sud
    0.08
    Activations Density 0.010%

    No Known Activations