© 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. 19-TRANSCODER-HP
    7. 8217
    Prev
    Next
    INDEX
    Explanations

    Personal narratives

    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
    èī°èĭ¦
    -0.33
    ä»ĺåĩº
    -0.30
    åıĹ伤
    -0.30
    说æĺİ
    -0.29
    åı¹
    -0.29
    ämp
    -0.29
     merc
    -0.28
    æī¿æĭħ
    -0.28
     cleaners
    -0.28
    èī°éļ¾
    -0.28
    POSITIVE LOGITS
     _$
    0.29
    cision
    0.29
    èĤī
    0.27
    -minute
    0.27
    quisitions
    0.26
    æĹłçŁ¥
    0.25
    inance
    0.25
    .Seek
    0.24
    urities
    0.24
    sexual
    0.23
    Activations Density 0.102%

    No Known Activations