© 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. 130467
    Prev
    Next
    INDEX
    Explanations

    first

    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
    åIJĪå½±
    -0.26
    羣缸
    -0.26
    ausible
    -0.26
    çĿģ
    -0.25
    assertTrue
    -0.25
    Sound
    -0.25
    对å¤ĸå¼ĢæĶ¾
    -0.25
     inventions
    -0.24
    eta
    -0.24
    ç¾İèªī
    -0.24
    POSITIVE LOGITS
    edom
    0.28
    Ùĥرة
    0.28
    utto
    0.28
    arks
    0.27
     crank
    0.27
    çon
    0.27
     mainly
    0.26
    KT
    0.25
    uhn
    0.25
    adem
    0.25
    Activations Density 0.277%

    No Known Activations