© 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. 130376
    Prev
    Next
    INDEX
    Explanations

    participate

    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
    ç´ł
    -0.29
    æıIJ示
    -0.26
     pops
    -0.26
     yal
    -0.23
    被åĪ¤
    -0.23
    bras
    -0.23
    ·»
    -0.23
    对åºĶ
    -0.23
    opus
    -0.22
    çĸ²æĥ«
    -0.22
    POSITIVE LOGITS
    Âł
    0.28
     Junction
    0.27
    rous
    0.25
     networks
    0.25
    åĬłçĽŁ
    0.25
    e
    0.25
    äºİ
    0.25
    ALA
    0.25
     directly
    0.24
    angible
    0.24
    Activations Density 0.099%

    No Known Activations