© 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. 107127
    Prev
    Next
    INDEX
    Explanations

    to

    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
    achinery
    -0.27
    Ñĥж
    -0.25
    -oriented
    -0.25
    -target
    -0.25
    ual
    -0.24
    NA
    -0.24
     targets
    -0.24
    -created
    -0.24
    ibles
    -0.24
    Teacher
    -0.24
    POSITIVE LOGITS
    ä½İä¸ĭ
    0.26
     prat
    0.25
    转载请
    0.24
    kart
    0.24
    éments
    0.24
    hof
    0.23
    称ä¹ĭ
    0.23
    ichtig
    0.23
    cciones
    0.23
    ä¸Ģè·¯
    0.23
    Activations Density 10.702%

    No Known Activations