© 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. 57923
    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
    eec
    -0.31
     pled
    -0.30
    ilarity
    -0.29
    èIJ
    -0.29
    ersions
    -0.26
    ByExample
    -0.26
     gover
    -0.26
    âĩIJ
    -0.25
    ä¸įè´Ł
    -0.25
     umb
    -0.24
    POSITIVE LOGITS
    åĬ«
    0.29
     prec
    0.28
    çĮ·
    0.25
    itis
    0.25
     represent
    0.24
    çĶ°
    0.24
    é»İ
    0.24
    prec
    0.24
    CAA
    0.24
    æĻĵå¾Ĺ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.