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. 11-TRANSCODER-HP
    4. 53790
    Prev
    Next
    INDEX
    Explanations

    doctor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以èī²
    -0.28
    å®ļçĤ¹
    -0.28
    >null
    -0.27
    å¾ģæ±Ĥ
    -0.27
    _that
    -0.27
    tees
    -0.26
    оÑī
    -0.26
    óż
    -0.25
    ieux
    -0.25
    _SHARE
    -0.24
    POSITIVE LOGITS
     wy
    0.29
    dy
    0.28
    chat
    0.27
    ä¸ĢéĿ¢
    0.27
    Chat
    0.27
     ay
    0.26
     wings
    0.26
    åĩ¹
    0.26
    studio
    0.25
    imations
    0.25
    Activations Density 0.207%

    No Known Activations