© 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. 64353
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hợp
    -0.25
    endale
    -0.25
    æ´Ĵ
    -0.24
    æĭī
    -0.23
    çļĤ
    -0.23
    gre
    -0.23
    é«ĺæ°´å¹³
    -0.23
     hostage
    -0.23
    interpre
    -0.22
     gre
    -0.22
    POSITIVE LOGITS
    è°ģèĥ½
    0.30
    åĴĮå®ĮåĸĦ
    0.25
    ованиÑı
    0.25
    à¸Ħà¸ĩ
    0.24
    çĬ°
    0.23
    rections
    0.23
    èĩªè´Ł
    0.23
    Users
    0.23
    hunt
    0.23
    onation
    0.23
    Activations Density 1.420%

    No Known Activations

    This feature has no known activations.