© 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. 6205
    Prev
    Next
    INDEX
    Explanations

    ?>č

    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
    itore
    -0.28
    åĩłåĪĨ
    -0.28
    è¿Ļåĩłä¸ª
    -0.26
    dl
    -0.26
    è¿Ļåĩł
    -0.26
    aml
    -0.25
     among
    -0.25
    è¿ĻéĩĮéĿ¢
    -0.25
    AML
    -0.25
    lâ
    -0.24
    POSITIVE LOGITS
    ä»įåľ¨
    0.26
    chez
    0.26
    秩
    0.25
    髯
    0.25
     Tee
    0.25
    åľ°çĤ¹
    0.24
    èĵĭ
    0.24
     honor
    0.24
     pathology
    0.23
    çĽĸ
    0.23
    Activations Density 0.011%

    No Known Activations