© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4791
    Prev
    Next
    INDEX
    Explanations

    Complex or uncertain statements

    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
    fs
    -0.29
    ieu
    -0.28
    GROUND
    -0.26
    _HOLD
    -0.26
    ignon
    -0.25
    ÑĪка
    -0.24
    -details
    -0.24
    ç´ł
    -0.23
    brates
    -0.23
    -control
    -0.23
    POSITIVE LOGITS
     Solution
    0.29
    solution
    0.29
    Solution
    0.28
    ä¸įçĽ¸ä¿¡
    0.27
     sharper
    0.25
    æ¶Ī失äºĨ
    0.24
    ä»İæĿ¥æ²¡æľī
    0.24
     solution
    0.24
    ä¸į解
    0.24
    æł¹æľ¬æ²¡æľī
    0.24
    Activations Density 0.022%

    No Known Activations