© 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. 20-TRANSCODER-HP
    7. 107708
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mers
    -0.28
     extr
    -0.27
    DR
    -0.26
    RF
    -0.26
    MER
    -0.25
    çĻ½é¢Ĩ
    -0.25
    zeÅĦ
    -0.25
     determin
    -0.25
    terminate
    -0.25
    door
    -0.24
    POSITIVE LOGITS
    èĢĮåİ»
    0.29
    phet
    0.29
    åİ»åĵªéĩĮ
    0.28
    _WS
    0.27
    åĪĽæĸ°åıijå±ķ
    0.27
    æľīçĶ¨
    0.27
    ä¼ļ让
    0.26
    é©·
    0.26
    èĢĮæĿ¥
    0.25
    çī¹æ´¾
    0.25
    Activations Density 8.725%

    No Known Activations