© 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. 97695
    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
    åIJŀ
    -0.25
    TERNAL
    -0.25
     outsiders
    -0.24
    å¤ĸéĿ¢
    -0.24
     Destiny
    -0.24
    SEE
    -0.23
    å®ŀæĸ½
    -0.23
    èİ´
    -0.23
     HIT
    -0.23
    wcs
    -0.23
    POSITIVE LOGITS
    ear
    0.29
    éľ²
    0.28
    bed
    0.28
    Greetings
    0.28
    lam
    0.27
    EAR
    0.27
    åĢĻ
    0.26
    efined
    0.26
     '**
    0.26
    ém
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.