© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    oppression

    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
    个
    -0.29
    icot
    -0.28
    çĥŃ度
    -0.27
    (\$
    -0.26
    edition
    -0.25
    _DIGEST
    -0.24
    every
    -0.24
    ä¸ĸçķĮä¸ĬæľĢ
    -0.24
    ój
    -0.23
    çłĶ究人åijĺ
    -0.23
    POSITIVE LOGITS
    @qq
    0.26
     unin
    0.26
     Near
    0.26
     unnecessary
    0.25
     transformative
    0.24
    /control
    0.24
    -like
    0.23
    åľ¨æĪijçľĭæĿ¥
    0.23
    对æĪijæĿ¥è¯´
    0.23
     candidacy
    0.23
    Activations Density 0.026%

    No Known Activations