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. 54191
    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
    åµĩ
    -0.30
    åģĩ
    -0.27
    _terms
    -0.25
    æĴ®
    -0.25
    æ¯ĹéĤ»
    -0.25
    è¿ĩé«ĺ
    -0.24
    åıĪ
    -0.24
     glyph
    -0.24
    jÄĻ
    -0.24
    å§Ķç»Ħç»ĩ
    -0.24
    POSITIVE LOGITS
    berger
    0.28
     Rockets
    0.27
    opic
    0.26
    quires
    0.26
    iflower
    0.25
    iline
    0.25
     Technologies
    0.25
    åĴ©
    0.25
    ugin
    0.24
    son
    0.24
    Activations Density 0.038%

    No Known Activations