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. 130188
    Prev
    Next
    INDEX
    Explanations

    Montgomery, Cole

    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
    é¢ĺ主
    -0.28
    ạ
    -0.28
    =train
    -0.27
    uida
    -0.27
    [train
    -0.27
    ú
    -0.26
    个交æĺĵ
    -0.24
    çī©
    -0.23
    )new
    -0.23
    TRAIN
    -0.23
    POSITIVE LOGITS
    LAY
    0.31
    çĽĶ
    0.28
    ISTIC
    0.28
     meno
    0.27
    holm
    0.27
     profess
    0.26
    plus
    0.26
     superf
    0.25
    åķ»
    0.25
    hl
    0.25
    Activations Density 0.002%

    No Known Activations