© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
     ry
    -0.25
    åºĦ严
    -0.24
    é»ī
    -0.24
    thers
    -0.24
     moden
    -0.24
    è¿Ļ段æŶéĹ´
    -0.23
     idea
    -0.23
     schooling
    -0.23
    æıIJä¾ĽäºĨ
    -0.22
     semester
    -0.22
    POSITIVE LOGITS
    ä¸Ģ举
    0.27
    ì§ľ
    0.26
    ItemClick
    0.26
    ļ
    0.25
    ipop
    0.25
    commons
    0.24
    åĹŁ
    0.24
    nick
    0.24
     tack
    0.23
    omid
    0.23
    Activations Density 0.003%

    No Known Activations