© 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. 6584
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    详ç»Ĩä»ĭç»į
    -0.27
    天åłĤ
    -0.26
    -square
    -0.26
    èĴĤ
    -0.25
    æ±Ģ
    -0.25
    ä½Ĩå®ĥ
    -0.24
    æĺ¯æĪijçļĦ
    -0.24
    让人
    -0.24
    rape
    -0.24
     sweet
    -0.24
    POSITIVE LOGITS
     indirectly
    0.27
    anean
    0.26
    /manual
    0.26
    大éĻĨ
    0.26
    èı°
    0.25
    大éĻ¸
    0.24
    omencl
    0.24
    ONA
    0.24
    azard
    0.24
    zac
    0.24
    Activations Density 0.017%

    No Known Activations