© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129501
    Prev
    Next
    INDEX
    Explanations

    consisting

    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
    culo
    -0.27
    ByVersion
    -0.27
    arez
    -0.26
    director
    -0.26
    inals
    -0.26
    ä¸ĢåŃĹ
    -0.26
    æ¬§çĽŁ
    -0.25
    itarian
    -0.24
    sonian
    -0.24
    =http
    -0.24
    POSITIVE LOGITS
     inplace
    0.27
    OLT
    0.26
     ké
    0.24
     overlapping
    0.24
    ä¸Ģå°ģ
    0.24
    解å¼Ģ
    0.24
    æij©æĵ¦
    0.24
    侯
    0.23
    _ke
    0.23
     Afr
    0.23
    Activations Density 0.012%

    No Known Activations