© 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. 23545
    Prev
    Next
    INDEX
    Explanations

    Web data extracts

    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
    Negative Logits
    unate
    -0.27
     —↵↵
    -0.26
    udent
    -0.26
    witch
    -0.25
    lse
    -0.25
    erties
    -0.25
    StateManager
    -0.24
    :hidden
    -0.24
    leitung
    -0.24
    :view
    -0.24
    POSITIVE LOGITS
    æݪ
    0.25
    æķ£åıij
    0.25
    enko
    0.24
    gu
    0.24
    çIJĨ解
    0.24
    çĪ¶äº²
    0.24
    æĺ¯åĽ½åĨħ
    0.24
    elig
    0.23
    æºIJ头
    0.23
     пок
    0.23
    Activations Density 0.016%

    No Known Activations