© 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. 25-TRANSCODER-HP
    7. 108832
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¥æĪ·
    -0.30
    avier
    -0.26
    è£ĺ
    -0.25
    do
    -0.24
     Keto
    -0.23
    çķĢ
    -0.23
    çª
    -0.23
     chalk
    -0.23
    ãĥĶãĥ¼
    -0.23
    *↵
    -0.22
    POSITIVE LOGITS
    翻身
    0.28
     cooperate
    0.27
    commons
    0.27
    å¿ı
    0.26
    ÑĦеÑĢ
    0.25
    æĬ¼
    0.25
    èįIJ
    0.25
    ailable
    0.25
    ä½ŀ
    0.25
     Davidson
    0.25
    Activations Density 0.916%

    No Known Activations