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. 54549
    Prev
    Next
    INDEX
    Explanations

    ats

    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
     RF
    -0.28
    è°Ł
    -0.26
    ChangeListener
    -0.26
     stay
    -0.25
    quo
    -0.25
     cheeses
    -0.24
    itarian
    -0.24
    isky
    -0.24
    åĬĽè¿ĺæĺ¯
    -0.23
    aub
    -0.23
    POSITIVE LOGITS
    è´Łæĭħ
    0.27
    express
    0.27
    endor
    0.27
    ndata
    0.27
    .numpy
    0.27
    ZE
    0.26
    emet
    0.26
    æ¯ĶåĪĨ
    0.26
    çīĮ
    0.25
    åĪĨå¸ĥ
    0.25
    Activations Density 0.008%

    No Known Activations