© 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. 8733
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Orientation
    -0.37
     orientation
    -0.34
     Direction
    -0.33
    Orientation
    -0.33
    Directions
    -0.31
     aligned
    -0.31
     Directions
    -0.30
     oriented
    -0.30
    Alignment
    -0.30
    -indent
    -0.30
    POSITIVE LOGITS
     trái
    0.26
    æĵį
    0.25
    åĪ·æĸ°
    0.25
    _drv
    0.25
     forthcoming
    0.24
    anium
    0.24
    èIJ¥åħ»ä»·åĢ¼
    0.24
    imir
    0.24
     undone
    0.24
     refresh
    0.23
    Activations Density 0.000%

    No Known Activations