© 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. 88958
    Prev
    Next
    INDEX
    Explanations

    .

    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
    Animating
    -0.30
    ixels
    -0.28
    animated
    -0.28
     animator
    -0.28
    tfoot
    -0.27
    èĭ±çī¹
    -0.27
    distinct
    -0.24
    DisplayName
    -0.24
    artists
    -0.23
     intent
    -0.23
    POSITIVE LOGITS
    ³³
    0.32
    ³³³
    0.31
    stra
    0.28
    Âł
    0.28
    urally
    0.25
    dera
    0.25
    _interface
    0.25
    éĻ¤åİ»
    0.24
    eil
    0.24
     sil
    0.24
    Activations Density 0.001%

    No Known Activations