© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    question answering

    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
    ä¼¼ä¹İ
    -0.36
    ä¼¼ä¹İæĺ¯
    -0.35
    忽
    -0.32
    çľĭä¸įåĩº
    -0.30
    ä¸įå°ijäºİ
    -0.28
     presumably
    -0.27
    ä¸į管
    -0.27
    ä¸įè¶ħè¿ĩ
    -0.27
    suggest
    -0.27
     seeming
    -0.27
    POSITIVE LOGITS
     because
    0.40
    åĽłä¸º
    0.39
    æĺ¯åĽłä¸º
    0.39
    because
    0.38
    åĽłä¸ºæĪij们
    0.38
    Because
    0.35
    åĽłçĤº
    0.33
    åĽłä¸ºä½ł
    0.33
     поÑĤомÑĥ
    0.32
     weil
    0.31
    Activations Density 0.110%

    No Known Activations