© 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. 88131
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code

    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
    agr
    -0.27
    ä¸įåı¯æĪĸ缺
    -0.26
    åįķè°ĥ
    -0.25
    AGR
    -0.25
    æĥ³åİ»
    -0.25
    å½¢
    -0.25
    riendly
    -0.25
     quint
    -0.24
     confident
    -0.24
    纤维
    -0.24
    POSITIVE LOGITS
    èĤ¡ä»·
    0.30
    æĬ¥è¡¨
    0.27
     Explorer
    0.25
    ä¸Ńè¶ħ
    0.25
    æĦį
    0.25
     Dep
    0.25
    por
    0.24
    eled
    0.24
    å½ĺ
    0.24
     incur
    0.23
    Activations Density 0.010%

    No Known Activations