© 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. 27-TRANSCODER-HP
    7. 9367
    Prev
    Next
    INDEX
    Explanations

    g

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİ»æī¾
    -0.28
    ä»İèĢĮ使
    -0.27
    annels
    -0.26
    æĿ¥æī¾
    -0.25
    ANCED
    -0.24
    equipment
    -0.24
    INGTON
    -0.24
    recipe
    -0.24
    mere
    -0.24
    åŁİ乡
    -0.24
    POSITIVE LOGITS
    athom
    0.28
    اع
    0.27
    éĽĨåĽ¢åħ¬åı¸
    0.26
    ä¹IJè§Ĥ
    0.26
    éĽĨåĽ¢
    0.26
    èĸ°
    0.24
    [at
    0.24
     Goblin
    0.23
     assess
    0.23
     Wall
    0.23
    Activations Density 0.002%

    No Known Activations