© 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. 87247
    Prev
    Next
    INDEX
    Explanations

    code, math, 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
     math
    -0.26
     Nest
    -0.26
     Char
    -0.26
     Translate
    -0.25
    çĥŁ
    -0.24
    tags
    -0.23
     оÑĩеÑĢедÑĮ
    -0.23
     economy
    -0.23
     base
    -0.23
    建æĪIJåIJİ
    -0.23
    POSITIVE LOGITS
    plers
    0.27
    aoke
    0.26
    emplace
    0.26
    èģĶ绾
    0.25
    移åĪ°
    0.25
    oubles
    0.25
    ÐĴидео
    0.24
    èle
    0.24
    æį
    0.24
    !--
    0.24
    Activations Density 0.000%

    No Known Activations