© 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. 30-TRANSCODER-HP
    7. 95490
    Prev
    Next
    INDEX
    Explanations

    GNU licenses, legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IEWS
    -0.27
    úa
    -0.26
     lows
    -0.25
     unfolded
    -0.24
    liwoÅĽci
    -0.24
    senal
    -0.24
    gÅĤo
    -0.24
    åıĶ
    -0.23
    è¿Ľç¨ĭä¸Ń
    -0.23
    nano
    -0.23
    POSITIVE LOGITS
    ä¸Ģèµ·
    0.34
     Together
    0.32
    åĽ¢
    0.31
    ä¸Ģèµ·æĿ¥
    0.29
    åľ¨ä¸Ģèµ·
    0.29
    Together
    0.28
    yme
    0.28
    ä¸Ģèµ·åİ»
    0.28
    arching
    0.27
    oki
    0.26
    Activations Density 0.100%

    No Known Activations