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. 7-TRANSCODER-HP
    4. 92758
    Prev
    Next
    INDEX
    Explanations

    ening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arium
    -0.27
     sighting
    -0.27
    åŃĺéĩı
    -0.25
     turnaround
    -0.25
    å¼Ĥåľ°
    -0.25
    cona
    -0.25
    ridor
    -0.24
    ific
    -0.24
     enh
    -0.24
     abruptly
    -0.24
    POSITIVE LOGITS
    æĿŁ
    0.29
    仲
    0.27
    andel
    0.27
    etti
    0.26
    íĨ¤
    0.25
    å¼Ł
    0.25
    饰
    0.25
    _weak
    0.25
     conveying
    0.24
    oga
    0.23
    Activations Density 0.002%

    No Known Activations