© 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. 57758
    Prev
    Next
    INDEX
    Explanations

    tree types

    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
     pow
    -0.28
    udad
    -0.27
    鬣
    -0.27
    .pow
    -0.26
    hora
    -0.25
    pow
    -0.25
    è¿Ļä¸Ģ天
    -0.24
    orial
    -0.24
    ])[
    -0.24
    TeV
    -0.24
    POSITIVE LOGITS
    upro
    0.28
    è§Ĩ
    0.27
    è°¦
    0.27
     Pandora
    0.26
    wit
    0.26
     gest
    0.25
    伸
    0.25
    sten
    0.24
    axy
    0.24
    yst
    0.24
    Activations Density 0.010%

    No Known Activations