© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    Punctuation/Code

    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
    å®ĺæĸ¹å¾®ä¿¡
    -0.29
    éļIJéļIJ
    -0.26
    éĶĻ
    -0.26
    奥æŀĹåĮ¹åħĭ
    -0.26
    éĿĻéĿĻ
    -0.26
    ãģ¨ãģ£ãģ¦ãĤĤ
    -0.26
    æī¹åıij
    -0.25
    æİ¥
    -0.25
    éĤ£æ¬¡
    -0.25
     Crom
    -0.24
    POSITIVE LOGITS
    cdb
    0.24
    иÑĤÑĮÑģÑı
    0.24
    speed
    0.24
     mt
    0.24
    apesh
    0.23
    è°ģçŁ¥éģĵ
    0.23
    ĶåĽŀ
    0.22
     kiÅŁi
    0.22
    fare
    0.22
    ickets
    0.22
    Activations Density 0.274%

    No Known Activations