© 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. 58045
    Prev
    Next
    INDEX
    Explanations

    Computer-related text

    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
     outside
    -1.53
    outside
    -1.35
     Outside
    -1.30
    å¤ĸçķĮ
    -1.26
    Outside
    -1.24
    å¤ĸéĿ¢
    -1.22
    å¤ĸéĥ¨
    -1.20
     external
    -1.13
    å¤ĸ
    -1.09
     exterior
    -1.05
    POSITIVE LOGITS
    -us
    0.25
     Cah
    0.23
     bois
    0.23
    overs
    0.23
     ngu
    0.22
    iller
    0.22
    ILI
    0.22
     lords
    0.21
     Oliv
    0.21
    usable
    0.21
    Activations Density 0.000%

    No Known Activations