© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    å±Ģ
    -0.27
    éĤ£ä¸Ģ
    -0.26
    å±Ģåī¯å±Ģéķ¿
    -0.26
    tu
    -0.25
    YYY
    -0.25
    ĤŃ
    -0.25
    training
    -0.24
    éĤ£äºº
    -0.24
     Appeal
    -0.24
    尤为éĩįè¦ģ
    -0.24
    POSITIVE LOGITS
    mlx
    0.26
    ç°¸
    0.26
    uba
    0.25
    opal
    0.25
    ró
    0.24
    eres
    0.24
    legen
    0.24
     *)&
    0.24
    .rar
    0.24
     RESOURCE
    0.23
    Activations Density 0.092%

    No Known Activations