© 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. 6909
    Prev
    Next
    INDEX
    Explanations

    counseling

    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
    #__
    -0.24
    inesis
    -0.24
    表æĢģ
    -0.22
    allocated
    -0.22
    _Items
    -0.21
    æŀľæ±ģ
    -0.21
    ä¼ļ议室
    -0.21
    partials
    -0.21
    ä¸Ģçŀ¬éĹ´
    -0.21
    è·Ľ
    -0.21
    POSITIVE LOGITS
    è´¹
    0.28
    arrant
    0.26
     sett
    0.26
     mell
    0.25
    tran
    0.24
     guilty
    0.24
    éĿ¢
    0.24
    agne
    0.24
    ical
    0.24
    lessness
    0.23
    Activations Density 0.687%

    No Known Activations