© 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. 129225
    Prev
    Next
    INDEX
    Explanations

    this

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īä¸ľè¥¿
    -0.26
    serter
    -0.25
    akov
    -0.25
    belt
    -0.25
    REFER
    -0.24
    ught
    -0.24
    -seat
    -0.24
    _Construct
    -0.24
    ä»Ģä¹Īäºĭ
    -0.24
    .vertices
    -0.24
    POSITIVE LOGITS
     phen
    0.25
     cre
    0.25
    è¶Ł
    0.24
     cres
    0.24
     essence
    0.24
    '],$
    0.23
     approximate
    0.23
     sus
    0.23
     growth
    0.23
     shared
    0.23
    Activations Density 0.029%

    No Known Activations