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. 72906
    Prev
    Next
    INDEX
    Explanations

    Medical/technical context

    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
    ãĥĮ
    -0.28
    bian
    -0.27
    OWN
    -0.26
     Sign
    -0.25
     span
    -0.25
     WN
    -0.24
    orman
    -0.24
    blank
    -0.24
    SPAN
    -0.24
    xf
    -0.23
    POSITIVE LOGITS
    ç¥ŀåύ
    0.26
    èī¯
    0.26
    æ¶Īè´¹èĢħçļĦ
    0.25
    {/
    0.25
    centre
    0.25
    èĭ¦æģ¼
    0.24
    ocache
    0.24
    atoria
    0.24
     اÙĦÙĥرÙĬÙħ
    0.24
    ç¼ĵ
    0.24
    Activations Density 0.007%

    No Known Activations