© 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. 8292
    Prev
    Next
    INDEX
    Explanations

    File assets

    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
    ç§ijæķĻ
    -0.27
    casting
    -0.26
    <label
    -0.26
    posted
    -0.26
    itary
    -0.26
    ivism
    -0.26
    пиÑĤ
    -0.25
    ystick
    -0.25
    icks
    -0.25
     Geh
    -0.25
    POSITIVE LOGITS
     assets
    0.32
     деп
    0.30
     Asset
    0.30
    -assets
    0.30
    glob
    0.29
     Assets
    0.29
     sass
    0.29
    _assets
    0.29
    èµĦ产
    0.29
    -watch
    0.28
    Activations Density 0.190%

    No Known Activations