© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6711
    Prev
    Next
    INDEX
    Explanations

    technical issues/support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chia
    -0.29
    eah
    -0.28
    é£Łåĵģå®īåħ¨
    -0.28
     Mood
    -0.26
    çĶŁåŃĺ
    -0.26
     Mug
    -0.25
    æ³¥
    -0.24
    æĶ¶æĶ¯
    -0.24
    çĹĽèĭ¦
    -0.24
    Oper
    -0.24
    POSITIVE LOGITS
    绿èī²éĢļéģĵ
    0.29
    è¿Ľåľº
    0.28
     pó
    0.27
    intern
    0.27
     Pens
    0.26
    æ±ī
    0.25
    åıĤ
    0.25
     mel
    0.25
    éĩĮ
    0.24
    æķķ
    0.24
    Activations Density 0.072%

    No Known Activations