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. 67519
    Prev
    Next
    INDEX
    Explanations

    souvenir

    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
    Õ³
    -0.30
    cad
    -0.28
    zsche
    -0.26
    icontains
    -0.26
     recall
    -0.26
    /GPL
    -0.26
    å°ļ
    -0.26
    çĭ¨
    -0.26
    oure
    -0.26
    çͳ
    -0.26
    POSITIVE LOGITS
    碳
    0.25
    athy
    0.25
     setter
    0.24
    ables
    0.24
     towing
    0.24
    atto
    0.24
     mai
    0.24
    _collection
    0.24
     swath
    0.23
     woodland
    0.23
    Activations Density 0.463%

    No Known Activations