© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1183
    Prev
    Next
    INDEX
    Explanations

    rankings and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    _signals
    -0.24
     Enables
    -0.24
    _drive
    -0.23
    _growth
    -0.23
    _stuff
    -0.22
    å·´å·´
    -0.22
    è¿Ļ家ä¼Ļ
    -0.22
    ç»ıè¿ĩå¤ļå¹´
    -0.22
     transports
    -0.22
     gw
    -0.21
    POSITIVE LOGITS
     awarded
    0.34
    表彰
    0.33
    å¥ĸ项
    0.32
     disqualified
    0.32
     prizes
    0.31
     awards
    0.30
    é¢ģåıij
    0.30
     contestant
    0.29
    åĪĽæĦı
    0.29
    èģĮ称
    0.29
    Activations Density 0.010%

    No Known Activations