© 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. 20-TRANSCODER-HP
    7. 141263
    Prev
    Next
    INDEX
    Explanations

    don

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FS
    -0.32
    FS
    -0.30
    zilla
    -0.29
     fs
    -0.29
    ties
    -0.27
    ÙĪت
    -0.27
     bookmarks
    -0.27
    ecom
    -0.26
     bookmark
    -0.25
    fs
    -0.25
    POSITIVE LOGITS
    ä¸Ģ线
    0.30
    igm
    0.27
    注æĺİåĩºå¤Ħ
    0.26
    оÑĩек
    0.26
    unnable
    0.26
    车åŃIJ
    0.26
    宽æĿ¾
    0.24
    _DEAD
    0.24
    =ax
    0.24
    缪
    0.24
    Activations Density 17.353%

    No Known Activations