© 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. 130509
    Prev
    Next
    INDEX
    Explanations

    Instructions and future actions

    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
    æľīä¸Ģç§į
    -0.27
    躯
    -0.27
     Accepted
    -0.27
    _accepted
    -0.26
    ä¸įä½ı
    -0.26
     bless
    -0.24
     accepts
    -0.24
    ins
    -0.24
    åħ»
    -0.24
    è¾¹ç¼ĺ
    -0.24
    POSITIVE LOGITS
    ä»Ĺ
    0.28
    å¿ħè¦ģ
    0.26
    iculty
    0.26
    ()",
    0.26
    泡
    0.25
    åĴİ
    0.25
    quate
    0.25
    itm
    0.25
    (depend
    0.25
    udu
    0.24
    Activations Density 0.005%

    No Known Activations