© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    code and data types

    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
    _HAVE
    -0.29
    液ä½ĵ
    -0.28
     liquids
    -0.28
     exp
    -0.26
    æ³Ĺ
    -0.25
     revived
    -0.24
    wend
    -0.24
     viv
    -0.24
    èĥľ
    -0.24
     اÙĦصادر
    -0.24
    POSITIVE LOGITS
    oise
    0.30
    aise
    0.27
    ination
    0.27
    iad
    0.27
    ControlItem
    0.26
    ois
    0.26
    ture
    0.26
    翻身
    0.25
    çĻ½é©¬
    0.25
    uddy
    0.25
    Activations Density 0.214%

    No Known Activations