© 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. 87773
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
    hus
    -0.28
    ä¸İä¼Ĺ
    -0.27
    .di
    -0.26
    个çĻ¾åĪĨ
    -0.26
    iveness
    -0.25
     versatile
    -0.24
    ulls
    -0.24
    æķĻèĤ²æķĻåѦ
    -0.24
    ",-
    -0.24
    ins
    -0.24
    POSITIVE LOGITS
    æİ¥
    0.27
    åħ¬ç«ĭ
    0.25
    èĦ±
    0.25
     Jeb
    0.24
     Kom
    0.24
    主页
    0.24
    underline
    0.24
    erable
    0.24
    itch
    0.23
    èĤĿ
    0.23
    Activations Density 0.005%

    No Known Activations