© 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. 97858
    Prev
    Next
    INDEX
    Explanations

    thanking visitors

    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
    éĩįçĤ¹
    -0.27
    æĢĢ
    -0.27
    åıij
    -0.26
    éĽĨä½ĵ
    -0.25
    วà¸Ķ
    -0.25
    ám
    -0.25
    èģĶåIJĪ
    -0.24
     heck
    -0.24
     Rap
    -0.24
     blasts
    -0.24
    POSITIVE LOGITS
     UIL
    0.30
    çļĦçĥŃæĥħ
    0.27
    ×ķף
    0.27
     nextProps
    0.24
    欤
    0.24
    eca
    0.24
    追éļı
    0.24
    æ°¤
    0.24
    èĵĬ
    0.24
     onSuccess
    0.24
    Activations Density 0.010%

    No Known Activations