© 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. 22-TRANSCODER-HP
    7. 88374
    Prev
    Next
    INDEX
    Explanations

    match

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     why
    -0.41
    为ä½ķ
    -0.40
    为ä»Ģä¹Ī
    -0.37
    ä½ķ
    -0.35
     Why
    -0.35
    çĤºä»Ģ麼
    -0.34
    æĽ·
    -0.34
    为ä»Ģä¹Īè¦ģ
    -0.34
    Why
    -0.34
    why
    -0.33
    POSITIVE LOGITS
     pairs
    0.33
    pairs
    0.31
    åĮ¹éħį
    0.29
     ing
    0.26
    éħį
    0.26
    ingles
    0.26
    ternal
    0.26
     personals
    0.26
    Pairs
    0.25
     stripper
    0.25
    Activations Density 0.035%

    No Known Activations