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. 14777
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    ILLA
    -0.27
    幡
    -0.24
    illas
    -0.24
    mk
    -0.24
    æ¶Ī
    -0.23
    æ¹®
    -0.23
     bracket
    -0.23
    *)
    -0.23
    apult
    -0.23
    vos
    -0.23
    POSITIVE LOGITS
    loid
    0.26
    rides
    0.25
    è¦
    0.24
    umes
    0.24
    éľ¾
    0.23
    åªļ
    0.23
    exampleInput
    0.23
    æĮĩçͲ
    0.23
    åĩºåħ¥
    0.23
    .slim
    0.23
    Activations Density 0.006%

    No Known Activations