© 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. 130646
    Prev
    Next
    INDEX
    Explanations

    Web interfaces/scraping

    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
    åįł
    -0.28
     fit
    -0.25
     MatSnackBar
    -0.25
    .ttf
    -0.25
     fitted
    -0.24
    æIJ¬
    -0.24
     fetched
    -0.24
     fits
    -0.24
     ÑĨена
    -0.24
    约åįł
    -0.23
    POSITIVE LOGITS
     Cliff
    0.28
    /aws
    0.28
    ä¹ĭå¤ĸ
    0.25
    ())->
    0.25
    dance
    0.23
    /graphql
    0.23
    éŨæĪ·
    0.23
    èĢ³æľµ
    0.23
    以ä¸ĬçļĦ
    0.23
    çĵ
    0.22
    Activations Density 0.000%

    No Known Activations