© 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. 20-TRANSCODER-HP
    7. 141913
    Prev
    Next
    INDEX
    Explanations

    instructions, actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kon
    -0.26
    _receive
    -0.25
      ↵
    -0.25
    -bs
    -0.25
    atched
    -0.24
     NK
    -0.24
    COLOR
    -0.24
    gh
    -0.24
    dcc
    -0.24
    æĮijåīĶ
    -0.24
    POSITIVE LOGITS
    åĨĻçĿĢ
    0.29
    oidal
    0.26
    riting
    0.25
    ä½Ľæ³ķ
    0.25
    mania
    0.25
     ench
    0.25
    æĪijä¸įæĥ³
    0.24
     اÙĦØ£Ùħ
    0.24
    arning
    0.23
    ınd
    0.23
    Activations Density 46.211%

    No Known Activations