© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97203
    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
    Negative Logits
    toa
    -0.26
     TimeUnit
    -0.25
    ä¹Łæľīä¸ĢäºĽ
    -0.24
     vid
    -0.23
     subj
    -0.23
    ENTA
    -0.23
    á»ijc
    -0.23
    seau
    -0.23
    NDAR
    -0.22
    çĤ¹èµŀ
    -0.22
    POSITIVE LOGITS
    åıĮéĩį
    0.28
    åİ¢
    0.28
    çī¢
    0.25
    ç¨ĭ度
    0.25
    èijĨ
    0.25
    %@
    0.24
    åĵªå®¶å¥½
    0.24
    flow
    0.24
    inceton
    0.24
    磫
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.