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. 53890
    Prev
    Next
    INDEX
    Explanations

    to

    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
    vara
    -0.29
    boro
    -0.26
    èݺ
    -0.26
    pecting
    -0.26
    yat
    -0.25
    åŁºæķ°
    -0.24
    onas
    -0.24
    主ä¹īæĢĿæĥ³
    -0.24
    flt
    -0.24
    (DataType
    -0.23
    POSITIVE LOGITS
    ä¸Ģçķª
    0.25
    åħ´ä¸ļ
    0.24
    临
    0.24
    å¹ħ度
    0.24
    _globals
    0.24
    åζ
    0.24
    åĪ»
    0.24
    è£ģå®ļ
    0.23
     Anch
    0.23
     outward
    0.23
    Activations Density 0.025%

    No Known Activations