© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    hyphens

    np_max-act-logits · gemini-2.0-flash
    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
    âĢIJ
    -0.33
     IonicPage
    -0.28
    ãĢij,ãĢIJ
    -0.26
     wise
    -0.26
    tors
    -0.25
    èĥ½å¤Łåľ¨
    -0.25
     haired
    -0.24
    æīĭæĦŁ
    -0.24
     maid
    -0.24
    ç¼ij
    -0.24
    POSITIVE LOGITS
    -↵
    0.28
    .-
    0.27
    -D
    0.27
    -between
    0.27
    -↵↵
    0.26
    ~-
    0.26
     expectedResult
    0.26
    å¾ģ
    0.26
    +-
    0.26
    enter
    0.25
    Activations Density 0.048%

    No Known Activations