© 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. 64191
    Prev
    Next
    INDEX
    Explanations

    Formal and technical writing

    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
    âĩĵ
    -0.29
    âĩij
    -0.28
    epad
    -0.28
    ImageContext
    -0.27
    wear
    -0.26
    lip
    -0.25
    忧
    -0.25
    忧èĻij
    -0.25
    elage
    -0.25
    liable
    -0.25
    POSITIVE LOGITS
    dup
    0.26
    ä¾Ľåħ»
    0.25
     duplication
    0.25
    abr
    0.25
    æĪªæŃ¢
    0.23
    ä½ij
    0.23
    éĢĤ
    0.23
     dost
    0.23
    è¯Ħ审
    0.23
     compression
    0.23
    Activations Density 1.174%

    No Known Activations