© 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. 58093
    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
     External
    -0.26
     alternative
    -0.26
    External
    -0.24
    ailable
    -0.24
    sher
    -0.23
    หมà¸Ķ
    -0.23
     responsiveness
    -0.23
    åľ¨æ¸¸æĪıä¸Ń
    -0.23
    躺çĿĢ
    -0.23
    ADB
    -0.23
    POSITIVE LOGITS
    æĭ¼
    0.28
     conditioning
    0.27
    armed
    0.27
    é¢ĦåijĬ
    0.25
    æīĢåľ¨çļĦ
    0.24
     arms
    0.24
    =title
    0.24
    å¹²æ¶ī
    0.24
     Arm
    0.23
     Vista
    0.23
    Activations Density 0.888%

    No Known Activations

    This feature has no known activations.