© 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. 23-TRANSCODER-HP
    7. 25276
    Prev
    Next
    INDEX
    Explanations

    gaining control/status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enim
    -0.26
    个交æĺĵ
    -0.25
    éĥ½æľīçĿĢ
    -0.24
    esters
    -0.23
    {|
    -0.23
    ä½ľèĢħæľ¬äºº
    -0.23
     mé
    -0.23
    ural
    -0.23
    ending
    -0.23
    èĻŀ
    -0.23
    POSITIVE LOGITS
    åįģæľĪ
    0.30
    å¾Īå¿«
    0.30
    anto
    0.28
    å°½æĹ©
    0.27
    æĭ¥
    0.26
     eventually
    0.26
    ä»İæѤ
    0.25
     progressively
    0.25
    çIJ°
    0.25
    尽快
    0.25
    Activations Density 0.016%

    No Known Activations