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. 73078
    Prev
    Next
    INDEX
    Explanations

    naming

    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
    ç§ij缮
    -0.30
    жд
    -0.25
    är
    -0.25
    .stdin
    -0.25
     Greeks
    -0.24
     pois
    -0.24
    åĢĻ
    -0.24
    溺
    -0.24
     Transmit
    -0.24
    åıĤæķ°
    -0.23
    POSITIVE LOGITS
    ستاÙĨ
    0.31
    å´Ľ
    0.26
    éŀħ
    0.26
    åľ°
    0.26
    æĮĤçīĮ
    0.25
    -of
    0.24
    -State
    0.24
    åľŁè±ª
    0.24
    IOR
    0.24
     offic
    0.24
    Activations Density 0.002%

    No Known Activations