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. 7-TRANSCODER-HP
    4. 1683
    Prev
    Next
    INDEX
    Explanations

    names and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äge
    -0.28
    imest
    -0.28
    nen
    -0.28
    诸
    -0.27
    -ob
    -0.26
    é¹Ĺ
    -0.25
    æĮĸæİĺ
    -0.25
    å΍
    -0.25
    -imm
    -0.25
    è¯įæĿ¡
    -0.25
    POSITIVE LOGITS
     cvs
    0.30
    ental
    0.27
     Guides
    0.26
    æľīè¶³å¤ŁçļĦ
    0.25
    æ½
    0.25
    пал
    0.24
    ent
    0.24
     psychosis
    0.24
     reductions
    0.24
     trú
    0.24
    Activations Density 0.001%

    No Known Activations