© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4897
    Prev
    Next
    INDEX
    Explanations

    =

    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
     Patt
    -0.29
    å¿ĥä¸ŃçļĦ
    -0.28
    æŃ£ç¢º
    -0.25
    _ur
    -0.25
    ç®ĹäºĨ
    -0.25
    çĶŁçIJĨ
    -0.24
    ç»ıæµİå¢ŀéķ¿
    -0.24
    (boost
    -0.23
    ä»ĺ
    -0.23
    éĤ
    -0.23
    POSITIVE LOGITS
     SME
    0.28
    olle
    0.28
    çı£
    0.27
     basic
    0.26
    çļĦåŁºæľ¬
    0.25
    alink
    0.25
    çĵĴ
    0.24
    ä¼ļ
    0.23
    çı°
    0.23
    çĴŀ
    0.23
    Activations Density 0.472%

    No Known Activations