© 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. 7239
    Prev
    Next
    INDEX
    Explanations

    code and 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
    èŃ°
    -0.29
     ang
    -0.26
     ëĶ°ëĿ¼
    -0.25
    ------+
    -0.24
    èĮ«èĮ«
    -0.24
    åĺ¹
    -0.24
    VERS
    -0.23
    áng
    -0.23
    -present
    -0.23
    inal
    -0.23
    POSITIVE LOGITS
    avar
    0.30
    éĢµ
    0.27
    rim
    0.27
    defaults
    0.24
    éľĨ
    0.24
    rito
    0.24
    ä¸»æľº
    0.24
    encent
    0.24
    ptr
    0.24
    é»ĺ认
    0.24
    Activations Density 0.019%

    No Known Activations