© 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. 87447
    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
     ns
    -0.26
    pring
    -0.25
     Twin
    -0.25
    ноп
    -0.25
    äºĨä»ĸçļĦ
    -0.24
    åĽŁ
    -0.24
    _Impl
    -0.24
    pol
    -0.24
    éĥ¨ä½į
    -0.24
    ä½Ĩæĺ¯ä»ĸ
    -0.24
    POSITIVE LOGITS
    ä¿¡çĶ¨
    0.26
    ause
    0.26
    usal
    0.26
    овÑĭм
    0.24
    aded
    0.24
    ilit
    0.24
    å¿ł
    0.24
     Mär
    0.24
    acity
    0.24
    çĹ´
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.