© 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. 87658
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    antro
    -0.28
    Pad
    -0.28
    éĢł
    -0.27
    åħ¬å®īå±Ģ
    -0.27
    pl
    -0.27
    0
    -0.27
    d
    -0.26
    å½¢æĪIJäºĨ
    -0.26
    ple
    -0.26
    æĭ¥
    -0.26
    POSITIVE LOGITS
    SEA
    0.30
    常è§ģçļĦ
    0.27
     setEmail
    0.27
    åĽ·
    0.26
    atee
    0.26
    ongyang
    0.26
    ñana
    0.26
    actics
    0.25
    hea
    0.25
    oire
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.