© 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. 4975
    Prev
    Next
    INDEX
    Explanations

    un

    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
    umm
    -0.28
    ums
    -0.28
    elder
    -0.27
    UM
    -0.27
     enjo
    -0.27
     mou
    -0.26
    راÙĨ
    -0.25
    icorn
    -0.24
    editable
    -0.24
    à¹īà¸Ńà¸Ļ
    -0.23
    POSITIVE LOGITS
    Overrides
    0.29
     Overrides
    0.27
     overrides
    0.26
    [unit
    0.26
    plies
    0.26
    [email
    0.25
    [word
    0.25
    ä¸īçĤ¹
    0.25
    ungan
    0.23
     reciprocal
    0.23
    Activations Density 0.030%

    No Known Activations