Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 54609
    Prev
    Next
    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderingContext
    -0.29
    ety
    -0.26
    [state
    -0.26
    lys
    -0.26
    .@
    -0.25
     Clyde
    -0.25
    NIL
    -0.24
    -AA
    -0.24
    èĤ¥
    -0.24
    PIX
    -0.23
    POSITIVE LOGITS
    çĸĥ
    0.26
    иÑĤ
    0.25
     surg
    0.24
    åΰåºķ
    0.24
    marvin
    0.24
    åΰåºķæĺ¯
    0.24
    ä»¶
    0.24
    elf
    0.23
    ansk
    0.23
    ëį°
    0.23
    Activations Density 0.014%

    No Known Activations