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. 24632
    Prev
    Next
    INDEX
    Explanations

    American

    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
     Che
    -0.28
    ạm
    -0.28
    Che
    -0.26
    itter
    -0.25
     che
    -0.25
    aces
    -0.24
     تع
    -0.24
     authors
    -0.24
    æĮ½
    -0.24
    ens
    -0.24
    POSITIVE LOGITS
    å°ģ
    0.31
    leground
    0.28
    imenti
    0.26
     Wizard
    0.25
    ç©°
    0.25
    æĦİ
    0.25
    à¹Ģà¸Ħรà¸Ķ
    0.24
    owards
    0.23
     trump
    0.23
     Suff
    0.23
    Activations Density 0.001%

    No Known Activations