© 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. 8117
    Prev
    Next
    INDEX
    Explanations

    new, advanced

    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
    (elements
    -0.29
     Namen
    -0.27
    çŃ¾è®¢äºĨ
    -0.26
    /she
    -0.26
    å¨ģåIJį
    -0.25
     requestCode
    -0.25
    åIJį声
    -0.25
    è¿Ļå¥Ĺ
    -0.25
    éĶĪ
    -0.25
    ëıħ
    -0.25
    POSITIVE LOGITS
     amidst
    0.27
    寤
    0.27
    iddle
    0.27
    'u
    0.25
    aking
    0.25
    æ´Ľåħĭ
    0.24
     taking
    0.24
    (withId
    0.24
    'av
    0.23
    ä¸Ĭè°ĥ
    0.23
    Activations Density 0.036%

    No Known Activations