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. 130079
    Prev
    Next
    INDEX
    Explanations

    helping verbs

    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
    inet
    -0.34
     warrants
    -0.28
    åı«æĪij
    -0.27
    æĬķèµĦé¡¹çĽ®
    -0.26
     unw
    -0.25
    ippy
    -0.25
    highlight
    -0.25
    omatic
    -0.25
     scal
    -0.24
     Lov
    -0.24
    POSITIVE LOGITS
    çļĦè¯Ŀé¢ĺ
    0.27
    ä¸Ńè¶ħ
    0.27
     //=
    0.27
     resourceName
    0.26
    resource
    0.25
    ären
    0.25
    prim
    0.24
    éĻªçĿĢ
    0.24
    _Generic
    0.24
    éĿ¢èī²
    0.24
    Activations Density 0.004%

    No Known Activations