© 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. 8684
    Prev
    Next
    INDEX
    Explanations

    )

    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
    èĨı
    -0.25
    iad
    -0.25
     Milky
    -0.24
    æĻķ
    -0.24
    nk
    -0.24
    ihu
    -0.23
    avenport
    -0.23
    æłĵ
    -0.23
    ousse
    -0.23
     HIM
    -0.23
    POSITIVE LOGITS
    çĴĭ
    0.33
    rega
    0.28
    icode
    0.28
    è§Ħç¨ĭ
    0.27
    enumerate
    0.24
    æijĺç¼ĸ
    0.24
    åIJ¦
    0.24
    ãĥĨãĥ¼ãĥŀ
    0.24
     tre
    0.23
    æīĭå·¥
    0.23
    Activations Density 0.025%

    No Known Activations