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. 326
    Prev
    Next
    INDEX
    Explanations

    oil and gas

    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
    空
    -0.28
    c
    -0.27
    empty
    -0.27
    à¸Ńà¸ģ
    -0.26
    .empty
    -0.26
    lig
    -0.26
    lt
    -0.26
     inter
    -0.25
    allowed
    -0.25
     empty
    -0.25
    POSITIVE LOGITS
    Slug
    0.28
    ?>>
    0.27
    _FAMILY
    0.26
    éĹ®æĪij
    0.24
    caster
    0.24
    æ°ĽåĽ´
    0.24
     conditioning
    0.24
    è¿´
    0.24
    heits
    0.23
     Mb
    0.23
    Activations Density 0.001%

    No Known Activations