© 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. 32-TRANSCODER-HP
    7. 43054
    Prev
    Next
    INDEX
    Explanations

    "no" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĿŀ
    -0.51
     non
    -0.49
     nond
    -0.44
    Non
    -0.43
     Non
    -0.43
    _non
    -0.39
     NON
    -0.39
    non
    -0.39
    -non
    -0.36
    (non
    -0.34
    POSITIVE LOGITS
     Sab
    0.27
    ena
    0.26
    请éĢīæĭ©
    0.25
    pot
    0.25
    .po
    0.25
     terminator
    0.24
    Sab
    0.24
    éĺ³åİ¿
    0.24
    erland
    0.24
     vem
    0.23
    Activations Density 0.010%

    No Known Activations