© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7885
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
    åľī
    -0.27
    åĽ½éĻħå¸Ĥåľº
    -0.26
    /Area
    -0.25
    /pg
    -0.25
    enor
    -0.25
    æĺŁæĺŁ
    -0.25
    ullet
    -0.25
    å´ģ
    -0.24
    AdminController
    -0.24
     INC
    -0.24
    POSITIVE LOGITS
     total
    0.28
    æĢ»éĩı
    0.27
    åĩĮæĻ¨
    0.26
    دÙĬÙĨ
    0.25
    Total
    0.25
    åĩºæīĭ
    0.24
    æĢ»æķ°
    0.24
    æĢ»
    0.24
    çĹħæĪ¿
    0.24
    ä½ľ
    0.24
    Activations Density 0.038%

    No Known Activations