© 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. 8429
    Prev
    Next
    INDEX
    Explanations

    semicolon (;)

    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
     lungs
    -0.27
     fins
    -0.27
     possession
    -0.26
    主æĮģ
    -0.25
     affirmative
    -0.25
     Vatican
    -0.25
    {text
    -0.24
     drums
    -0.24
    pressor
    -0.24
    Bel
    -0.24
    POSITIVE LOGITS
    tributes
    0.31
    unte
    0.28
    (skill
    0.26
    çīĮåŃIJ
    0.25
    åł°
    0.25
    è§Ĵ度
    0.24
    ufe
    0.24
    æļĤ
    0.24
    émon
    0.24
    Reflect
    0.24
    Activations Density 0.010%

    No Known Activations