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. 125908
    Prev
    Next
    INDEX
    Explanations

    the

    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
    rams
    -0.29
    ewn
    -0.28
    _negative
    -0.28
    ymes
    -0.27
    enze
    -0.27
    RAW
    -0.27
    _TW
    -0.26
    Tw
    -0.26
    nts
    -0.25
    ipi
    -0.24
    POSITIVE LOGITS
     yourselves
    0.31
     himself
    0.30
     yourself
    0.29
     herself
    0.27
    empor
    0.26
     ourselves
    0.26
     oneself
    0.26
     ÑģебÑı
    0.25
    æıIJåΰ
    0.25
    -inc
    0.24
    Activations Density 0.059%

    No Known Activations