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. 24139
    Prev
    Next
    INDEX
    Explanations

    nature

    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
    erson
    -0.28
    colo
    -0.27
    getSingleton
    -0.25
    thal
    -0.25
    è¡·
    -0.25
    iali
    -0.25
     dumps
    -0.24
    esso
    -0.24
    iaux
    -0.24
    OLL
    -0.24
    POSITIVE LOGITS
     wij
    0.29
    ä¸ĢéĹª
    0.28
     @{$
    0.26
    åħħè£ķ
    0.25
    æķijçģ¾
    0.25
    eu
    0.25
    éĩį度
    0.25
    ozo
    0.24
    ucker
    0.24
    èĥľ
    0.24
    Activations Density 0.001%

    No Known Activations