© 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. 9-TRANSCODER-HP
    7. 29500
    Prev
    Next
    INDEX
    Explanations

    .gov

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºı
    -0.28
    èĩ³ä¸Ĭ
    -0.26
    _SIGNATURE
    -0.25
    atég
    -0.25
    æݼ
    -0.25
     remote
    -0.24
    _deep
    -0.24
     decks
    -0.24
    çĽĴåŃIJ
    -0.24
    @qq
    -0.23
    POSITIVE LOGITS
    飲
    0.28
    饮æĸĻ
    0.27
    é£ĺ
    0.25
    饮çĶ¨
    0.25
    zburg
    0.25
    avo
    0.25
     zwar
    0.25
    ONLY
    0.24
     bib
    0.24
    amic
    0.24
    Activations Density 0.760%

    No Known Activations