© 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. 9089
    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
    å·¾
    -0.27
    é¬ĥ
    -0.26
    é¦ĸ
    -0.25
    itzer
    -0.25
    Advertisements
    -0.24
     Redistributions
    -0.24
    .ObjectId
    -0.24
    /Foundation
    -0.24
    æĹħ
    -0.23
     Atatürk
    -0.23
    POSITIVE LOGITS
    orre
    0.26
    骥
    0.25
     assignable
    0.25
    åı¯æĥ³
    0.24
    epad
    0.24
     recurs
    0.24
    è¨Ģ论
    0.23
    èĪ·
    0.23
    缮çļĦåľ¨äºİ
    0.23
    çļĦç§ĺå¯Ĩ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.