© 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. 22-TRANSCODER-HP
    7. 111514
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    io
    -0.28
    éľ²
    -0.26
    age
    -0.26
     former
    -0.25
    car
    -0.25
    z
    -0.24
    kin
    -0.24
    cio
    -0.24
    fra
    -0.24
    ett
    -0.23
    POSITIVE LOGITS
    MDB
    0.28
    缴èĩ³
    0.26
    _every
    0.26
     inev
    0.25
    ACP
    0.24
    ãģĪãĤĭ
    0.24
    xFB
    0.23
    aring
    0.23
    ä¸įéĹ´
    0.23
    MenuStrip
    0.23
    Activations Density 0.037%

    No Known Activations