© 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. 4737
    Prev
    Next
    INDEX
    Explanations

    programming 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
    -strong
    -0.27
     Grades
    -0.27
    ardin
    -0.26
    -variable
    -0.25
    è¶Ĭ好
    -0.24
    »¿
    -0.24
    æł¼
    -0.24
     Strap
    -0.24
    emax
    -0.24
    éĢĭ
    -0.24
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.47
    æļĤæŶ
    0.39
    æļĤ
    0.38
     prelim
    0.37
    åĪĿ级
    0.35
     preliminary
    0.34
    æļ«
    0.33
     Prel
    0.33
    éĺ¶æ®µ
    0.31
     initial
    0.28
    Activations Density 0.130%

    No Known Activations