© 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. 58155
    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
    -ves
    -0.30
    ä½ĵ积
    -0.29
     summ
    -0.29
    vd
    -0.27
    vla
    -0.27
    æľĪä¸ĭ
    -0.27
    èµĮ
    -0.26
    beb
    -0.26
    æľ¬ç½ij
    -0.26
     OMIT
    -0.26
    POSITIVE LOGITS
    çĶŁçIJĨ
    0.26
    bestos
    0.25
    CDATA
    0.25
     só
    0.25
    _TypeInfo
    0.24
    æİĴ
    0.24
     Semaphore
    0.24
     lý
    0.24
     cin
    0.24
     close
    0.23
    Activations Density 0.000%

    No Known Activations