© 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. 98872
    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
    å¢ĥåĨħ
    -0.30
    joy
    -0.28
    å¢ĥ
    -0.27
    uju
    -0.27
    haps
    -0.26
    æīĵåĩ»
    -0.26
    让å®ĥ
    -0.26
    à¸Ĺà¸ĺ
    -0.26
    åľ¨æĹ¥æľ¬
    -0.26
    _heads
    -0.25
    POSITIVE LOGITS
    çıŃ
    0.26
    haul
    0.26
    éĿŀ常é«ĺ
    0.25
    fork
    0.25
    ynchronously
    0.25
    볬
    0.24
    ijkl
    0.24
     LIN
    0.23
     &)
    0.23
    ights
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.