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. 46444
    Prev
    Next
    INDEX
    Explanations

    istinguish

    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
    çĨı
    -0.24
    ARGV
    -0.24
    egr
    -0.24
    ermint
    -0.23
    anked
    -0.23
     Lana
    -0.23
    iÄį
    -0.23
    crate
    -0.23
    inar
    -0.23
    uggest
    -0.23
    POSITIVE LOGITS
    pii
    0.29
    lea
    0.28
    felt
    0.26
    åįĩåѦ
    0.25
     ado
    0.24
    æĸŃ
    0.24
     overload
    0.24
    ainter
    0.24
    aps
    0.23
    ä¹ĭå®¶
    0.23
    Activations Density 0.140%

    No Known Activations