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. 15355
    Prev
    Next
    INDEX
    Explanations

    iss

    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
    har
    -0.31
    ives
    -0.30
    ue
    -0.28
     gu
    -0.28
    hi
    -0.26
    rag
    -0.25
    ÑĢам
    -0.25
     coroutine
    -0.24
    apr
    -0.24
    Coroutine
    -0.24
    POSITIVE LOGITS
    ughs
    0.25
     Glam
    0.25
    人éĢī
    0.25
     compilers
    0.24
    azor
    0.24
    ä¸ľè¥¿
    0.24
    èµ°åĬ¿åĽ¾
    0.24
    $L
    0.23
    èĻı
    0.23
    iniz
    0.23
    Activations Density 0.001%

    No Known Activations