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. 24162
    Prev
    Next
    INDEX
    Explanations

    words with prefixes/suffixes

    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
    ż
    -0.26
    ÃŃvel
    -0.26
    orgh
    -0.25
    o
    -0.25
    å¢ŀå̼æľįåĬ¡
    -0.25
    çĦ¶èĢĮ
    -0.25
    滤
    -0.24
    åıĤè°ĭ
    -0.24
    åŁĩ
    -0.24
    ossa
    -0.24
    POSITIVE LOGITS
    nc
    0.28
    ç¥
    0.27
    ipt
    0.26
    odelist
    0.26
    incy
    0.25
     STRICT
    0.24
    ntp
    0.24
    èĨ¨
    0.24
    -exp
    0.24
     impunity
    0.23
    Activations Density 0.003%

    No Known Activations