© 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. 9128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    elic
    -0.30
    ercul
    -0.29
    们çļĦ
    -0.29
    ocop
    -0.28
    etur
    -0.27
    illions
    -0.25
    们éĥ½
    -0.25
    äºĭåIJİ
    -0.25
    纯æ´ģ
    -0.25
    orado
    -0.25
    POSITIVE LOGITS
    åı¯çĶ¨
    0.28
    çļĦ第ä¸Ģ个
    0.27
    AND
    0.26
    çİ»çĴĥ
    0.26
    åºĶ该æĺ¯
    0.26
     Mort
    0.25
    a
    0.25
     glass
    0.25
    é¢ĺ缮
    0.25
    b
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.