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. 10291
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ergy
    -0.28
    dy
    -0.26
    airy
    -0.26
    mo
    -0.25
    bl
    -0.25
    blem
    -0.25
    ary
    -0.24
    åĬŀçIJĨ
    -0.24
    ÅĤow
    -0.24
    æĶ¾åģĩ
    -0.24
    POSITIVE LOGITS
    UCH
    0.27
    éĤ£æ®µ
    0.26
     simulator
    0.25
    好å¥ĩ
    0.25
     echoed
    0.25
     Simulator
    0.25
     Reconstruction
    0.25
    pheres
    0.24
    åıĤ
    0.24
    {/
    0.24
    Activations Density 0.001%

    No Known Activations