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. 24126
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    FromClass
    -0.32
    utely
    -0.31
    :variables
    -0.26
    íĢ´
    -0.26
     Arist
    -0.25
     perplex
    -0.24
    uglify
    -0.24
    serie
    -0.24
    lingen
    -0.24
    setEnabled
    -0.24
    POSITIVE LOGITS
    ys
    0.32
    ion
    0.29
    -go
    0.27
    pool
    0.27
    wer
    0.26
    çĶŁåŃĺ
    0.26
    erra
    0.26
     r
    0.26
    aders
    0.25
    表示
    0.25
    Activations Density 0.001%

    No Known Activations