© 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. 130652
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ordes
    -0.28
    AsyncResult
    -0.27
    arsed
    -0.27
    aeda
    -0.26
    unt
    -0.26
    VML
    -0.26
    eda
    -0.26
    å¼Ĥåľ°
    -0.25
    亲
    -0.25
    CLR
    -0.25
    POSITIVE LOGITS
     Shut
    0.29
    iplina
    0.27
    LineNumber
    0.26
    line
    0.26
    è¨ĢãģĦ
    0.26
    çľ¼åīį
    0.25
    åħ³éĶ®åŃĹ
    0.25
     Line
    0.25
    æ´»çĿĢ
    0.25
     gs
    0.24
    Activations Density 0.572%

    No Known Activations