© 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. 129906
    Prev
    Next
    INDEX
    Explanations

    scientific articles

    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
     molecule
    -0.35
     molecules
    -0.31
     proteins
    -0.29
     carb
    -0.28
    oster
    -0.28
     forms
    -0.27
     amino
    -0.27
    RefCount
    -0.26
     compounds
    -0.26
    swer
    -0.26
    POSITIVE LOGITS
    æ¯Ľ
    0.30
    åıĸ
    0.29
    顾
    0.29
    åĴĮå¹³
    0.28
    缼
    0.27
    åĶIJ
    0.27
    å½Ń
    0.27
    åħħ
    0.26
    éĹ·
    0.26
    å¥Ĺ
    0.26
    Activations Density 0.011%

    No Known Activations