© 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. 56725
    Prev
    Next
    INDEX
    Explanations

    .VisualStudio

    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
    称ä¹ĭ
    -0.28
     Worlds
    -0.27
    .isArray
    -0.26
    onian
    -0.26
    memo
    -0.25
    .Globalization
    -0.25
    èĢģ乡
    -0.24
    nze
    -0.24
    æĥij
    -0.24
    åĽ½éĻħå¸Ĥåľº
    -0.24
    POSITIVE LOGITS
    mps
    0.30
    ORY
    0.28
     hum
    0.28
    æŸ
    0.27
    odore
    0.27
     victim
    0.25
    çĥŃ
    0.24
    (Dense
    0.24
    -validator
    0.24
    çĽ¸å¯¹
    0.24
    Activations Density 0.002%

    No Known Activations