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. 24372
    Prev
    Next
    INDEX
    Explanations

    of

    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
     pinnacle
    -0.31
    çªģåıij
    -0.30
    .minimum
    -0.29
    panic
    -0.28
    æľĢ
    -0.28
     nhất
    -0.28
    alsy
    -0.26
    otti
    -0.26
    minimum
    -0.26
    åŀ«
    -0.26
    POSITIVE LOGITS
    eners
    0.28
    âĸ¾
    0.27
    wave
    0.26
     wave
    0.26
    backs
    0.25
    eh
    0.25
     Surre
    0.25
    以æŃ¤
    0.24
    abar
    0.24
    룸
    0.24
    Activations Density 0.003%

    No Known Activations