© 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. 9026
    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
     snapped
    -0.30
    代
    -0.26
     identities
    -0.26
    atoire
    -0.26
     minim
    -0.26
    over
    -0.25
    gar
    -0.25
     identity
    -0.25
    atory
    -0.25
     trimest
    -0.25
    POSITIVE LOGITS
    .jupiter
    0.27
    æ¶ĪåĮĸ
    0.27
     DeepCopy
    0.27
     Dash
    0.25
     queryInterface
    0.25
    alytics
    0.25
    enus
    0.24
    ä¼ļéķ¿
    0.24
     ru
    0.24
    ä¸įå¦Ĥ
    0.24
    Activations Density 0.084%

    No Known Activations

    This feature has no known activations.