© 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. 88871
    Prev
    Next
    INDEX
    Explanations

    other/unknown

    np_max-act · gemini-2.0-flash
    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
     legalize
    -0.30
    Ĥæķ°
    -0.28
    emain
    -0.27
    ician
    -0.26
    FINE
    -0.25
    fäll
    -0.25
     uninitialized
    -0.25
    åģĮ
    -0.25
    è¥Ħ
    -0.24
    ’T
    -0.23
    POSITIVE LOGITS
    rollo
    0.28
    èµ·æĿ¥äºĨ
    0.27
     tables
    0.26
    èĢĮå·²
    0.25
    пÑĥÑģк
    0.24
    cole
    0.23
    ä¸Ģå®ļèĥ½
    0.23
    éĥ½èĥ½
    0.23
    ÑĢоÑĪ
    0.23
    onical
    0.23
    Activations Density 0.003%

    No Known Activations