© 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. 57521
    Prev
    Next
    INDEX
    Explanations

    Characters and deities

    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
    å¿ĥæĥ³
    -0.26
    æ²¥
    -0.25
     juni
    -0.25
    maids
    -0.23
    uite
    -0.23
     pylint
    -0.23
    -relative
    -0.23
     hearts
    -0.23
    -gradient
    -0.22
    icum
    -0.22
    POSITIVE LOGITS
    代表æĢ§
    0.27
    Äĥng
    0.26
     altogether
    0.26
    èIJ½åĪ°
    0.25
    人çī©
    0.25
    æ²ĵ
    0.25
    å¾·
    0.25
    vation
    0.24
    æ¡©
    0.24
     favoured
    0.24
    Activations Density 0.001%

    No Known Activations