© 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. 41921
    Prev
    Next
    INDEX
    Explanations

    medical or names

    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
    é»ĺ
    -0.31
    äh
    -0.29
    Had
    -0.26
    çĥŃ线
    -0.26
    cap
    -0.25
    had
    -0.25
     rolling
    -0.25
    ialis
    -0.24
    avier
    -0.24
     surf
    -0.24
    POSITIVE LOGITS
    elon
    0.32
    Ħ件
    0.28
    _Level
    0.27
    emb
    0.27
    Levels
    0.26
    onet
    0.26
    _levels
    0.25
     NU
    0.25
     level
    0.25
    å²IJ
    0.25
    Activations Density 0.003%

    No Known Activations