© 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. 130419
    Prev
    Next
    INDEX
    Explanations

    banking

    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
    lined
    -0.25
    çģ¯çģ«
    -0.25
    rat
    -0.24
     warranty
    -0.23
    éļ¾çĤ¹
    -0.23
     +#+
    -0.23
    å§Ķå±Ī
    -0.23
    رش
    -0.23
    ása
    -0.23
    åľ¨ä¸Ģ个
    -0.23
    POSITIVE LOGITS
    åħ¬åijĬ称
    0.27
    åĮºåŁŁåĨħ
    0.26
    gregation
    0.25
    æĺ¯ä»ĸ
    0.25
     corporation
    0.23
    born
    0.23
     sinc
    0.23
    vious
    0.23
    =row
    0.23
    åĪ°
    0.23
    Activations Density 11.274%

    No Known Activations