© 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. 88480
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    FN
    -0.30
    主页
    -0.28
    åį¸
    -0.26
    ãģ°ãģĭãĤĬ
    -0.25
    .tokens
    -0.25
    åİĨåı²æĸ°
    -0.24
     Euros
    -0.24
    CTL
    -0.24
    æĸ°åŀĭåĨł
    -0.24
     MLM
    -0.24
    POSITIVE LOGITS
    幸
    0.26
    åĩŃ
    0.24
    sub
    0.24
    åĸľ
    0.24
    otherapy
    0.24
    land
    0.23
    æĸĩåĮĸ建设
    0.23
     yat
    0.23
    rug
    0.23
    è¿ĻçĤ¹
    0.23
    Activations Density 0.461%

    No Known Activations