© 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. 108206
    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
    çıĢ
    -0.25
    éĺµ
    -0.25
    åĽº
    -0.25
     alone
    -0.24
    INESS
    -0.24
    eous
    -0.24
    วา
    -0.23
    esium
    -0.23
     dip
    -0.23
    AndWait
    -0.23
    POSITIVE LOGITS
    plug
    0.27
     plug
    0.27
    对æĪij们
    0.25
    å¯¹ä½ł
    0.25
    å½Ĵå±ŀäºİ
    0.25
     verbosity
    0.24
     reductions
    0.24
     attends
    0.24
    ĥĿ
    0.24
    èİĨ
    0.24
    Activations Density 0.656%

    No Known Activations

    This feature has no known activations.