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. 160
    Prev
    Next
    INDEX
    Explanations

    hemisphere

    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
    èĻ¹æ¡¥
    -0.27
    çϾç§ij
    -0.26
    oppers
    -0.26
    追踪
    -0.25
    èįł
    -0.24
     filtered
    -0.23
     hyp
    -0.23
    upro
    -0.23
    urrection
    -0.23
     esp
    -0.23
    POSITIVE LOGITS
     goodwill
    0.27
    /reg
    0.26
    .VERSION
    0.25
    {name
    0.24
    ONY
    0.24
    /Internal
    0.24
    oya
    0.24
    ortal
    0.23
    .Locale
    0.22
    scri
    0.22
    Activations Density 7.016%

    No Known Activations