© 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. 112457
    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
    STE
    -0.28
    çĤ½
    -0.27
    angel
    -0.25
    åĪ«
    -0.25
     болÑĮÑĪ
    -0.25
    æ¦ľ
    -0.24
    built
    -0.24
    åIJ¹
    -0.24
    —to
    -0.23
    ç¿ĺ
    -0.23
    POSITIVE LOGITS
     Duis
    0.27
    xAD
    0.25
    spb
    0.25
    opies
    0.25
    ä¾ĿéĿł
    0.24
    æ¶İ
    0.24
    AxisSize
    0.24
    pend
    0.24
    upe
    0.24
    ubits
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.