© 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. 141804
    Prev
    Next
    INDEX
    Explanations

    the

    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
    è£Ļ
    -0.31
     devs
    -0.30
    è¡Įéķ¿
    -0.30
    è¿ĺå¾Ĺ
    -0.27
    DataRow
    -0.26
     discipl
    -0.25
    grounds
    -0.24
    ä»İä¸ļèĢħ
    -0.23
    å®ļåIJij
    -0.23
    illac
    -0.23
    POSITIVE LOGITS
    itt
    0.27
     strengths
    0.25
    à¸ķำ
    0.25
    íĥĢ
    0.25
    under
    0.25
    ÑĥÑĤ
    0.25
    lah
    0.24
    泸
    0.24
    é³ħ
    0.24
    èĤ²
    0.24
    Activations Density 17.324%

    No Known Activations