© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97372
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    åģļçļĦ
    -0.26
    .RemoveAll
    -0.25
    ése
    -0.25
    åĵªä¸ª
    -0.24
     superior
    -0.24
    Directories
    -0.24
    åı¹
    -0.24
     LogLevel
    -0.24
    ocator
    -0.24
     Revelation
    -0.23
    POSITIVE LOGITS
     Ger
    0.25
    _SLOT
    0.25
    лез
    0.24
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.24
    ä»İ严
    0.24
    whether
    0.24
    Ger
    0.24
    cons
    0.24
     whether
    0.23
    æĺ¯åIJ¦åŃĺåľ¨
    0.23
    Activations Density 0.006%

    No Known Activations