© 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. 58070
    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
    积水
    -0.32
    å¥ĸåĬ±
    -0.30
    iser
    -0.28
     suicides
    -0.24
    æĻļæľŁ
    -0.24
    大è¡Ĺ
    -0.24
     mer
    -0.24
     Eng
    -0.24
    inne
    -0.23
     track
    -0.23
    POSITIVE LOGITS
    atég
    0.31
    udio
    0.29
    ãĤıãĤĬ
    0.29
    elijke
    0.28
    -board
    0.28
     bothers
    0.27
    åĿIJä¸ĭ
    0.26
    _TBL
    0.26
    conde
    0.25
    _back
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.