© 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. 14-TRANSCODER-HP
    7. 40456
    Prev
    Next
    INDEX
    Explanations

    Worms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    身å¿ĥ
    -0.28
     freezes
    -0.27
    åĽłåľ°
    -0.26
    身ä½ĵ
    -0.25
    blocking
    -0.25
    grounds
    -0.24
    ç²¾
    -0.24
    å¼łå®¶çķĮ
    -0.24
    mps
    -0.24
    辩è¯ģ
    -0.24
    POSITIVE LOGITS
    çŃĶåį·
    0.29
    çļĦçŃĶæ¡Ī
    0.28
    åºĵ
    0.28
     Ðijо
    0.27
    dorf
    0.27
     Cornel
    0.26
    ORB
    0.26
    Fred
    0.25
    kek
    0.25
    åĬ©æĶ»
    0.24
    Activations Density 1.311%

    No Known Activations