© 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. 64026
    Prev
    Next
    INDEX
    Explanations

    atics

    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
    åıĬ缸åħ³
    -0.29
    æİī
    -0.28
    UBLIC
    -0.26
    outu
    -0.25
     gef
    -0.25
    ãģłãģijãģ§ãģªãģı
    -0.25
    åıĬåħ¶ä»ĸ
    -0.25
    åıĬåħ¶
    -0.24
    åĻ¨
    -0.24
    åıĬ
    -0.24
    POSITIVE LOGITS
    äºĽä»Ģä¹Ī
    0.25
    åľį
    0.24
    åıijå¸ĥåħ¬åijĬ
    0.24
    åĽ´
    0.24
     uw
    0.23
     urlpatterns
    0.23
     ca
    0.23
    çĶ¨é¤IJ
    0.23
    .EventHandler
    0.23
     handlers
    0.23
    Activations Density 79.025%

    No Known Activations