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. 46421
    Prev
    Next
    INDEX
    Explanations

    database searches

    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
     journals
    -0.26
     cartel
    -0.26
     prefixes
    -0.25
    åį°è®°
    -0.25
    åĮ¹
    -0.25
    æĸ¯é¡¿
    -0.24
     breadcrumbs
    -0.23
    ãĤĵãģ©
    -0.23
    onnement
    -0.23
     circles
    -0.22
    POSITIVE LOGITS
    odate
    0.31
    å·½
    0.28
    åĩºåĬ¨
    0.25
    èĭį
    0.24
    posed
    0.24
    hq
    0.24
     Passed
    0.24
    xFA
    0.24
     passed
    0.24
    _gui
    0.24
    Activations Density 0.016%

    No Known Activations