© 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. 129718
    Prev
    Next
    INDEX
    Explanations

    Code, files, or Portuguese

    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
    itude
    -0.32
    缮åīįæŃ£åľ¨
    -0.27
    æĬķæľº
    -0.27
    æĹ¥åIJİ
    -0.26
    åľ¨è¿Ļç§į
    -0.26
    å·²ä¹ħçļĦ
    -0.26
    .MEDIA
    -0.25
    ients
    -0.25
    ãģĮãĤī
    -0.24
     kern
    -0.24
    POSITIVE LOGITS
    ucer
    0.33
    åħ·ä½ĵåĨħ容
    0.30
    åĽ½äºº
    0.28
     enumerate
    0.28
    éĿ¢ç§¯çº¦
    0.27
    åħ·ä½ĵ
    0.25
    NW
    0.25
    IVER
    0.25
    人大
    0.25
    ucken
    0.25
    Activations Density 0.011%

    No Known Activations