© 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. 112237
    Prev
    Next
    INDEX
    Explanations

    utilize

    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
    oret
    -0.26
    outlined
    -0.25
    _weak
    -0.24
    èĪĨ论
    -0.24
    agon
    -0.24
    ç¿ĺ
    -0.23
    æĿı
    -0.23
    äºļåĨĽ
    -0.23
    ħ§
    -0.22
    游
    -0.22
    POSITIVE LOGITS
     biod
    0.28
    ä¸Ģå®ļçļĦ
    0.24
     Beds
    0.24
    人家
    0.24
    ationToken
    0.24
     employ
    0.24
    è±ķ
    0.23
    มหา
    0.23
    ÅĤ
    0.23
     thumb
    0.22
    Activations Density 0.239%

    No Known Activations