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. 53373
    Prev
    Next
    INDEX
    Explanations

    accidents and safety

    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
    ä¸Ńåħ³
    -0.28
     off
    -0.27
    tte
    -0.26
     transcription
    -0.25
     trans
    -0.25
    èµ°äºĨ
    -0.25
    Off
    -0.24
    cription
    -0.24
    mode
    -0.24
    -off
    -0.24
    POSITIVE LOGITS
    apters
    0.29
    authenticated
    0.27
    è¿Ļåĩłä¸ª
    0.27
     ogóle
    0.26
     authenticated
    0.25
     thÄĥm
    0.24
    _roles
    0.24
    oubted
    0.24
     Contacts
    0.24
     dresser
    0.24
    Activations Density 0.012%

    No Known Activations