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. 146873
    Prev
    Next
    INDEX
    Explanations

    month

    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
     GIVEN
    -0.32
    shine
    -0.30
    æĥħæĢĢ
    -0.26
    湿润
    -0.26
    èį¡
    -0.25
    arsi
    -0.25
     Laws
    -0.25
     cleanliness
    -0.25
     moist
    -0.25
    vetica
    -0.24
    POSITIVE LOGITS
    äºĺ
    0.30
    iesz
    0.26
    /dom
    0.25
    ä¸ĸ代
    0.24
    å½±åĥı
    0.24
    꺼
    0.24
    èĩªä¹ł
    0.24
    æĹ¥è®°
    0.24
    æĬ
    0.24
     Catal
    0.24
    Activations Density 0.024%

    No Known Activations