© 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. 98261
    Prev
    Next
    INDEX
    Explanations

    smoking

    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
    è¾¹
    -0.30
    éĤĬ
    -0.26
     weighed
    -0.24
    Äį
    -0.23
    è´Ŀ
    -0.23
    edom
    -0.23
    side
    -0.23
     separated
    -0.23
    èµĸ
    -0.23
    è¿Ļå¥Ĺ
    -0.23
    POSITIVE LOGITS
     misc
    0.26
    unist
    0.25
    ák
    0.24
    é¢ĨåŁŁçļĦ
    0.24
    hil
    0.24
     ula
    0.23
    bish
    0.23
     khoá
    0.23
    åIJĮå¿Ĺ
    0.23
    --č↵
    0.22
    Activations Density 0.032%

    No Known Activations