© 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. 9288
    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
    à¤Ŀ
    -0.24
    æīĢ以æĪij
    -0.24
    resher
    -0.24
    POSITORY
    -0.23
    jom
    -0.23
    ercul
    -0.23
    è¸
    -0.23
    unter
    -0.23
    è½®æµģ
    -0.23
     timespec
    -0.23
    POSITIVE LOGITS
    çĪµå£«
    0.29
    åĪ¥
    0.27
     Concert
    0.26
    -lang
    0.26
    åĪ«
    0.25
    iane
    0.25
    Author
    0.25
     cg
    0.24
    çİĦ
    0.24
    author
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.