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. 7-TRANSCODER-HP
    4. 97989
    Prev
    Next
    INDEX
    Explanations

    anc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tape
    -0.29
    ILED
    -0.28
    çļĦ人çī©
    -0.27
    tape
    -0.26
     Carp
    -0.26
    eries
    -0.26
    ç»Ń
    -0.25
    主è§Ĥ
    -0.25
    å±ŀ
    -0.25
    ingroup
    -0.25
    POSITIVE LOGITS
    æĹ¨
    0.27
    åĪĨå±Ģ
    0.25
     combin
    0.24
    اÙħر
    0.24
    åķĦ
    0.24
    roat
    0.23
    æ·±åħ¥æİ¨è¿Ľ
    0.23
    Equivalent
    0.23
    çĽĴåŃIJ
    0.23
    gradient
    0.23
    Activations Density 0.004%

    No Known Activations