© 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. 57264
    Prev
    Next
    INDEX
    Explanations

    limit

    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
     ImVec
    -0.27
    .gs
    -0.26
    дÑĢа
    -0.26
    vak
    -0.26
    ims
    -0.25
    åıªåī©
    -0.25
    TeX
    -0.25
    (strip
    -0.24
    aim
    -0.24
    çľģ
    -0.24
    POSITIVE LOGITS
     how
    0.30
     opportunities
    0.27
    åѦçĶŁçļĦ
    0.27
     attacks
    0.26
    ä¸Ĭçľĭ
    0.26
     fal
    0.25
     exit
    0.25
    äºĨå¤ļå°ij
    0.25
     thumb
    0.25
    ä¹ĭä½ľ
    0.25
    Activations Density 0.126%

    No Known Activations