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. 27-TRANSCODER-HP
    4. 1009
    Prev
    Next
    INDEX
    Explanations

    ref

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intr
    -0.25
     bran
    -0.25
     muss
    -0.25
    è¾Ń
    -0.25
    yms
    -0.24
    #End
    -0.24
    _salary
    -0.24
    processable
    -0.24
     accountable
    -0.24
    ardy
    -0.24
    POSITIVE LOGITS
    é¥ŃåºĹ
    0.30
    aired
    0.27
    éģģ
    0.26
     Huck
    0.26
    elihood
    0.25
    ields
    0.24
    åŀĤ
    0.24
    obi
    0.24
    eson
    0.24
    å¾ĹæĦı
    0.24
    Activations Density 0.995%

    No Known Activations