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. 46916
    Prev
    Next
    INDEX
    Explanations

    help requests

    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
    Od
    -0.25
    igy
    -0.24
    .entries
    -0.24
    ä½Ļå®¶
    -0.24
    APO
    -0.24
    ertino
    -0.24
    跨度
    -0.23
     sóc
    -0.23
    çļĵ
    -0.23
    $txt
    -0.23
    POSITIVE LOGITS
    ured
    0.25
    å¤Ħå¤Ħ
    0.25
    P
    0.24
     stabilized
    0.24
    uity
    0.24
    ature
    0.24
    .lex
    0.24
    (
    0.24
    å®ī
    0.23
    /com
    0.23
    Activations Density 0.005%

    No Known Activations