© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 88174
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.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¿Ŀæ³ķ
    -0.26
     exceeding
    -0.25
    _wave
    -0.25
    èĮ¬
    -0.25
    fan
    -0.24
     relevant
    -0.24
    ermint
    -0.24
     concluding
    -0.24
    orgot
    -0.24
     resembling
    -0.23
    POSITIVE LOGITS
    äºİæŃ¤
    0.28
     live
    0.27
    culate
    0.26
    live
    0.25
     analyses
    0.25
    æĬĵ
    0.25
     Ars
    0.25
     leash
    0.25
     LIVE
    0.25
    les
    0.24
    Activations Density 0.006%

    No Known Activations