© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42387
    Prev
    Next
    INDEX
    Explanations

    HTML and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kart
    -0.27
    èī²ç´ł
    -0.27
     lib
    -0.26
    ook
    -0.26
    igen
    -0.26
    ä¸ĩåħ¬éĩĮ
    -0.26
    楷
    -0.26
    çľģåĨħ
    -0.25
    ket
    -0.25
    ItemSelected
    -0.25
    POSITIVE LOGITS
    æīĺ
    0.28
    è¯łéĩĬ
    0.27
    åľ°çĤ¹
    0.27
    ãģ¾ãģ¾
    0.26
    Cluster
    0.26
     equip
    0.25
    ç¾İ
    0.25
     cluster
    0.25
    衬
    0.25
    汶
    0.25
    Activations Density 0.003%

    No Known Activations