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. 0-TRANSCODER-HP
    4. 51
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªæķij
    -0.29
    iales
    -0.29
    æ¢Ń
    -0.28
    athlon
    -0.27
    oteca
    -0.26
    çͰéĩİ
    -0.26
    ibia
    -0.25
    avers
    -0.25
    Äĥ
    -0.25
     consc
    -0.24
    POSITIVE LOGITS
    仪表
    0.27
    hen
    0.27
     diffuse
    0.25
    ?family
    0.25
    =min
    0.24
     foil
    0.24
     ~(
    0.24
    sheet
    0.23
    /on
    0.23
    pio
    0.23
    Activations Density 5.521%

    No Known Activations