© 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. 130701
    Prev
    Next
    INDEX
    Explanations

    testing knowledge and skills

    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
    Donate
    -0.28
    åıijå±ķæĸ¹åIJij
    -0.28
    å¾ģæĶ¶
    -0.26
    éĤ£å°±æĺ¯
    -0.26
    è¾Ĺ
    -0.25
    äºĭçī©
    -0.25
    æ¡ħ
    -0.25
    ÐĹа
    -0.24
    Mahon
    -0.24
     Donate
    -0.24
    POSITIVE LOGITS
    olib
    0.32
    aina
    0.27
    åĪ¥
    0.26
     discharged
    0.26
    \web
    0.25
     webs
    0.25
    饱
    0.25
     doch
    0.25
    ç½ij
    0.24
    eos
    0.24
    Activations Density 8.925%

    No Known Activations