© 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. 12-TRANSCODER-HP
    7. 22376
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¥
    -0.29
    -know
    -0.27
    bullet
    -0.27
    ethod
    -0.26
    ctor
    -0.25
    åł±
    -0.25
     retrie
    -0.25
    bos
    -0.25
    éĢĹ
    -0.24
    çĿ£åĬŀ
    -0.24
    POSITIVE LOGITS
    ivia
    0.28
    ounder
    0.28
     Searches
    0.27
    èµ¢å¾Ĺ
    0.27
    èĮĹ
    0.26
    ighth
    0.25
    :href
    0.25
    èłĥ
    0.24
    èįª
    0.24
    ä»ij
    0.24
    Activations Density 0.001%

    No Known Activations