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. 53863
    Prev
    Next
    INDEX
    Explanations

    rine soluble

    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
    è¦ģç´§
    -0.29
    agh
    -0.25
     wirk
    -0.25
     mÃŃ
    -0.24
    ni
    -0.24
    ¹Ħ
    -0.23
    edImage
    -0.23
    mention
    -0.23
    ä»Ģ麽
    -0.23
    顽
    -0.23
    POSITIVE LOGITS
    маÑĤеÑĢиал
    0.28
    åįķä»·
    0.27
    ç²īæľ«
    0.26
    _mut
    0.26
    ;++
    0.26
    PPP
    0.26
    ä¸Ģæ³¢
    0.26
    åıijçݰ
    0.25
    åıijçݰäºĨ
    0.25
    oupon
    0.25
    Activations Density 0.069%

    No Known Activations