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. 23-TRANSCODER-HP
    4. 771
    Prev
    Next
    INDEX
    Explanations

    Personal thoughts and reflections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ģä¹Ī
    -0.30
     Spicer
    -0.29
     *&
    -0.28
    侬
    -0.27
    æ¢Ĩ
    -0.27
    è¡Įè´¿
    -0.26
    -solid
    -0.26
    çīĴ
    -0.26
     */)
    -0.26
    edException
    -0.26
    POSITIVE LOGITS
     feeling
    0.29
     out
    0.28
     wondering
    0.27
    使æĪij
    0.27
     ponder
    0.27
    ением
    0.26
    æĦŁåΰ
    0.26
     presented
    0.25
     suddenly
    0.25
     BS
    0.25
    Activations Density 0.034%

    No Known Activations