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. 4134
    Prev
    Next
    INDEX
    Explanations

    density

    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
    rewrite
    -0.28
    selectors
    -0.27
    è¤Ĵ
    -0.26
    rabbit
    -0.26
    å¹¿åľº
    -0.25
     Setter
    -0.25
    redd
    -0.25
    scheme
    -0.25
    fraction
    -0.24
    å¿ĥåĬ¨
    -0.24
    POSITIVE LOGITS
    apg
    0.29
    ona
    0.27
    oning
    0.27
    onic
    0.26
    大å®Ĺ
    0.25
     smb
    0.25
    ä¼łç»Ł
    0.25
    aju
    0.24
    gars
    0.24
    [,]
    0.24
    Activations Density 0.027%

    No Known Activations