© 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. 23-TRANSCODER-HP
    7. 24559
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯æĪijçļĦ
    -0.40
    äºĨæĪijçļĦ
    -0.37
    æ¯ĶæĪij
    -0.35
    æĺ¯æĪij
    -0.34
    æĪijçļĦ
    -0.33
    è¿Ļæĺ¯æĪij
    -0.33
     ìłľê°Ģ
    -0.30
    æĪijçļĦå¿ĥ
    -0.29
     my
    -0.29
    æĪijåĴĮ
    -0.29
    POSITIVE LOGITS
    ä»İä¸ļèĢħ
    0.35
    ä¼ģä¸ļåĴĮ
    0.32
     ngÆ°á»Ŀi
    0.31
    å½ĵäºĭ
    0.31
    ä¸Ģ个人
    0.30
    çĶ¨æĪ·çļĦ
    0.29
    çĶ¨æĪ·
    0.28
    使çĶ¨èĢħ
    0.27
     اÙĦÙħسÙĦÙħ
    0.27
     ICommand
    0.27
    Activations Density 0.003%

    No Known Activations