© 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. 7698
    Prev
    Next
    INDEX
    Explanations

    common

    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
    宣è¨Ģ
    -0.30
    åĬłéĩį
    -0.30
    utors
    -0.28
    æĹłæķĪ
    -0.26
    æĹłå£°
    -0.26
    ÑģеÑĢ
    -0.26
     Sed
    -0.26
    rive
    -0.25
    æĹĮ
    -0.25
     invis
    -0.25
    POSITIVE LOGITS
    egade
    0.27
    æĺ¨
    0.26
    gmail
    0.26
    æľ«
    0.26
    .Live
    0.25
    å¹´ä¹ĭä¹ħ
    0.25
    è¿ij两年
    0.25
    reload
    0.25
    itaire
    0.25
    mÄ±ÅŁtı
    0.24
    Activations Density 0.019%

    No Known Activations