© 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. 141818
    Prev
    Next
    INDEX
    Explanations

    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
     remains
    -0.28
    ouch
    -0.28
    aden
    -0.26
    adel
    -0.26
    SHOT
    -0.25
    ascar
    -0.25
    mate
    -0.24
     undoubtedly
    -0.24
     Against
    -0.24
     deserves
    -0.24
    POSITIVE LOGITS
     realised
    0.27
     Ramsey
    0.25
    èµĶä»ĺ
    0.25
    /wiki
    0.24
    åŦ
    0.24
     Rodrigo
    0.24
    ussy
    0.24
     Raspberry
    0.23
    ç¯Ĩ
    0.23
    arith
    0.23
    Activations Density 4.085%

    No Known Activations