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. 11-TRANSCODER-HP
    4. 146317
    Prev
    Next
    INDEX
    Explanations

    rather/instead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inous
    -0.26
     ActivityCompat
    -0.26
    åıĮéĩį
    -0.25
    åľ¨æ¸¸æĪıä¸Ń
    -0.25
    gency
    -0.25
    tsy
    -0.25
    assin
    -0.24
    illon
    -0.24
    è´Ł
    -0.24
    ornment
    -0.24
    POSITIVE LOGITS
    wares
    0.27
    çķħ
    0.26
    igar
    0.26
    click
    0.25
    wg
    0.25
     spared
    0.25
    æĪ·åı£
    0.25
    ä¸Ģå®¶
    0.24
    çIJĨæĥ³
    0.24
    骥
    0.24
    Activations Density 0.099%

    No Known Activations