© 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. 108637
    Prev
    Next
    INDEX
    Explanations

    name

    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
     Capital
    -0.28
    èľķ
    -0.27
    æĬij
    -0.27
    tere
    -0.26
    ÂŃt
    -0.26
     inflated
    -0.26
     Basket
    -0.26
    åħħè£ķ
    -0.26
    imit
    -0.25
     CAPITAL
    -0.25
    POSITIVE LOGITS
    æĢ»ä½ĵ
    0.29
    è¯Ħ
    0.26
    çIJĨ论
    0.26
    Mui
    0.25
    anks
    0.25
     troubles
    0.24
    温度
    0.23
    çĩĥçĥ§
    0.23
    zym
    0.23
    張貼
    0.23
    Activations Density 0.953%

    No Known Activations