© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7175
    Prev
    Next
    INDEX
    Explanations

    Time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsEmpty
    -0.27
    genden
    -0.25
    è´¯
    -0.25
    鸱
    -0.25
    åºĵéĩĮ
    -0.24
    æĦıè¯Ĩ
    -0.24
    å¾ģä¿¡
    -0.24
     GPLv
    -0.24
    ÑĥÑī
    -0.23
     panc
    -0.23
    POSITIVE LOGITS
    æ¯ıå½ĵ
    0.27
    enant
    0.26
    æıIJ款
    0.26
    unde
    0.25
    æ¯ıå¹´éĥ½
    0.25
     hel
    0.24
    ãĥ¼ãĤ¹
    0.24
    åĢ¼å¾Ĺ
    0.24
    æ¯ı次éĥ½
    0.24
     hand
    0.24
    Activations Density 0.037%

    No Known Activations