© 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. 20-TRANSCODER-HP
    7. 107909
    Prev
    Next
    INDEX
    Explanations

    expressing opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounc
    -0.26
    icorn
    -0.25
     Tutor
    -0.24
    _Handler
    -0.24
    oins
    -0.24
     quant
    -0.24
    uil
    -0.23
    ÙĥÙĨ
    -0.23
     ez
    -0.23
    OUN
    -0.23
    POSITIVE LOGITS
     noticed
    0.26
    -bel
    0.26
    éģŃåĪ°
    0.25
    Recogn
    0.24
     possibilities
    0.24
    ossible
    0.24
    osti
    0.23
    urgeon
    0.23
    使åħ¶
    0.23
     Recogn
    0.23
    Activations Density 19.777%

    No Known Activations