© 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. 8768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĽijæĬ¤
    -0.26
    çĥ
    -0.26
    aped
    -0.25
     Hammer
    -0.25
    etter
    -0.25
     YEARS
    -0.24
    typing
    -0.24
    åģļå®Į
    -0.24
    loat
    -0.24
    unnable
    -0.23
    POSITIVE LOGITS
    çģ°èī²
    0.31
    æĭ¾
    0.30
    ä¸Ģ个å°ı
    0.25
    åĮħåIJ«äºĨ
    0.25
    çīĪæĿĥå½Ĵ
    0.24
    ç©¿
    0.24
    ä¿ĥè¿ĽäºĨ
    0.24
    æĭ£
    0.23
    iden
    0.23
    ires
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.