© 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. 8178
    Prev
    Next
    INDEX
    Explanations

    code or scientific text

    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
     nan
    -0.59
    纳米
    -0.55
     nano
    -0.48
    nan
    -0.47
    nano
    -0.44
     Nan
    -0.43
    .nan
    -0.43
    Nano
    -0.43
     nm
    -0.39
     Nano
    -0.38
    POSITIVE LOGITS
    èįIJ
    0.28
    åĪ¤
    0.26
     ONLINE
    0.26
     epile
    0.25
    apur
    0.24
     aug
    0.24
    akter
    0.24
     NEO
    0.24
    á»įng
    0.23
    çĪĨ
    0.23
    Activations Density 0.005%

    No Known Activations