© 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. 41000
    Prev
    Next
    INDEX
    Explanations

    inflammation

    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
    itches
    -0.28
    ure
    -0.28
    åıĤ
    -0.26
    alla
    -0.25
    fs
    -0.25
    æ¯ıæ¯ı
    -0.24
    äºĨä¸Ģ个
    -0.24
    Vent
    -0.23
     Monk
    -0.23
    çļĦè¯Ŀ
    -0.23
    POSITIVE LOGITS
     resend
    0.30
    _hpp
    0.29
    çı©
    0.27
    æ±°
    0.26
    èĻŁ
    0.26
    ptest
    0.26
    éĥ½ä¸įä¼ļ
    0.25
    gnore
    0.25
     reused
    0.25
    åħ¶ä»ĸåĽ½å®¶
    0.25
    Activations Density 1.020%

    No Known Activations