© 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. 20-TRANSCODER-HP
    7. 63277
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĥĤ
    -0.27
    æѤæŶ
    -0.26
    ÑģÑĤÑĢой
    -0.25
    Exited
    -0.24
    便åĪ©
    -0.24
    angement
    -0.24
    ×Ĵ×ķ
    -0.24
    å½ĵåľ°
    -0.23
    èijĽ
    -0.23
    éĴ§
    -0.23
    POSITIVE LOGITS
    itaire
    0.29
     ReSharper
    0.26
    rimp
    0.26
    è¿Ŀæ³ķçĬ¯ç½ª
    0.25
     Crime
    0.25
    acre
    0.25
     crime
    0.25
    åĪijäºĭ责任
    0.24
    -collapse
    0.24
    ết
    0.24
    Activations Density 2.796%

    No Known Activations