© 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. 20-TRANSCODER-HP
    7. 63398
    Prev
    Next
    INDEX
    Explanations

    a the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Untitled
    -0.28
    ETY
    -0.27
    çĪ¬
    -0.26
    æ¸Ĭ
    -0.24
    elijk
    -0.24
    utorial
    -0.23
    ç¡Ŀ
    -0.23
    äºĮåŃĹ
    -0.23
     Mexicans
    -0.23
    å°Ĩèĩªå·±çļĦ
    -0.23
    POSITIVE LOGITS
    Compatibility
    0.28
    èĹıçĿĢ
    0.27
    éĽĨåĽ¢èĤ¡ä»½
    0.27
     compat
    0.26
    åħ¼å®¹
    0.25
     ;-)
    0.25
     Compatible
    0.25
    æł¸å®ļ
    0.25
    Compat
    0.25
     transl
    0.24
    Activations Density 24.649%

    No Known Activations