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. 0-TRANSCODER-HP
    4. 0
    Prev
    Next
    INDEX
    Explanations

    diss

    np_max-act · gemini-2.0-flash

    words beginning with the “diss-” prefix.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IDE
    -0.28
    oner
    -0.27
    _mA
    -0.26
    igs
    -0.26
     ide
    -0.25
     setId
    -0.25
     IDEA
    -0.24
     sealing
    -0.24
    asty
    -0.23
    edi
    -0.23
    POSITIVE LOGITS
    <dd
    0.25
    ieve
    0.24
    assic
    0.24
    /tag
    0.24
    thur
    0.23
    oop
    0.23
     coordinated
    0.23
    -double
    0.23
    éļ§
    0.22
    ordinated
    0.22
    Activations Density 5.003%

    No Known Activations