© 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. 97719
    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
    窦
    -0.28
    çļĦéĤ£ä¸Ģ
    -0.26
     MUT
    -0.26
    éĤ£ä¸Ģ
    -0.26
    IMIT
    -0.25
    çĤ·
    -0.25
    ä¾ij
    -0.25
    æĪijçľĭ
    -0.24
    ALK
    -0.24
    (mut
    -0.24
    POSITIVE LOGITS
     elsewhere
    0.27
    æıIJé«ĺ
    0.27
    ä¸įæĺİ
    0.27
    综åIJĪ
    0.26
    ä¸Ģ个人
    0.26
     Trap
    0.25
     refr
    0.25
    vens
    0.25
    å¼Ģå§ĭ
    0.25
     trap
    0.25
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.