© 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. 141169
    Prev
    Next
    INDEX
    Explanations

    panic

    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
    éĴľ
    -0.29
     uncertainties
    -0.27
    SOFTWARE
    -0.26
    ä¸į解
    -0.26
    åīį身
    -0.25
    åľ¨ä»ĸçļĦ
    -0.25
    Rnd
    -0.25
    è·¡
    -0.24
    ç½Ĥ
    -0.24
     Raleigh
    -0.24
    POSITIVE LOGITS
    lessly
    0.29
    宫
    0.28
     instant
    0.28
     instantly
    0.27
     add
    0.26
    levard
    0.26
    amm
    0.26
     list
    0.25
    à¹Ī
    0.25
    çĸ½
    0.25
    Activations Density 1.582%

    No Known Activations