© 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. 129194
    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
    ä»ĸæĺ¯ä¸Ģ个
    -0.27
    æĹ¶æľº
    -0.27
    amps
    -0.26
    æѤ类
    -0.25
    ceph
    -0.25
    æĥħåĨµ
    -0.25
     Bedford
    -0.25
     Installed
    -0.25
    senal
    -0.24
     ÑģÑĤеп
    -0.24
    POSITIVE LOGITS
    cv
    0.29
    pla
    0.29
    å»ĵ
    0.25
     voter
    0.24
    eyJ
    0.24
     Cv
    0.24
    urator
    0.24
    validator
    0.24
     pity
    0.24
    _:
    0.23
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.