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. 7453
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    vas
    -0.29
    æ´ĭ
    -0.25
    ×ķ׳×ķת
    -0.24
    tec
    -0.24
     hier
    -0.24
     Vas
    -0.24
     allegiance
    -0.24
    æĵį纵
    -0.23
    è±IJ
    -0.23
    altern
    -0.23
    POSITIVE LOGITS
    大家åĪĨ享
    0.28
     rtl
    0.27
    rtc
    0.26
    请çĤ¹åĩ»
    0.26
    ä¸Ģä½ĵåĮĸ
    0.24
    ä¼ļå½±åĵį
    0.24
     fellowship
    0.24
     Palest
    0.24
    _san
    0.24
    æ¾Ħæ¸ħ
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.