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. 2-TRANSCODER-HP
    4. 164
    Prev
    Next
    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lies
    -0.27
    abble
    -0.26
    åı°
    -0.26
    ipel
    -0.26
    /tutorial
    -0.25
    booking
    -0.25
    edException
    -0.24
    arial
    -0.24
    antal
    -0.24
    itaire
    -0.24
    POSITIVE LOGITS
    (:,:,
    0.28
    кÑĢаÑĤ
    0.27
    笺
    0.27
    Ns
    0.27
    è¿ĻäºĽéĹ®é¢ĺ
    0.26
     Taste
    0.25
     Season
    0.25
    åİŁæĿ¥çļĦ
    0.25
    isons
    0.25
       
    0.24
    Activations Density 34.594%

    No Known Activations