© 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. 112373
    Prev
    Next
    INDEX
    Explanations

    Software, technology, companies

    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
    çĽijå¯Ł
    -0.31
    lich
    -0.29
    rep
    -0.28
    åĪ¶éĢł
    -0.27
     rep
    -0.27
    泪
    -0.26
    建åįİ
    -0.26
    rips
    -0.25
    	rep
    -0.25
    导æ¼Ķ
    -0.25
    POSITIVE LOGITS
    quia
    0.32
    quette
    0.28
     Bob
    0.25
     Bowen
    0.24
    _Source
    0.24
    avan
    0.24
    å¥¹åľ¨
    0.23
    çĶµåŃIJ产åĵģ
    0.23
     WIN
    0.23
     distinct
    0.23
    Activations Density 0.011%

    No Known Activations