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. 92898
    Prev
    Next
    INDEX
    Explanations

    shutting down

    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
    untu
    -0.28
    cer
    -0.27
    æĴµ
    -0.26
    ä¸įå¿į
    -0.26
    ç¾ŀ
    -0.25
    æģķ
    -0.25
    æĭĬ
    -0.25
    itional
    -0.24
    itions
    -0.24
    ä¿¡ç͍
    -0.24
    POSITIVE LOGITS
    æıIJèµ·
    0.26
     sands
    0.26
     Owen
    0.25
    agrams
    0.24
    animated
    0.24
    åıįå°Ħ
    0.24
    xxx
    0.24
     traff
    0.24
    esser
    0.23
     Resolution
    0.23
    Activations Density 0.002%

    No Known Activations