© 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. 130708
    Prev
    Next
    INDEX
    Explanations

    Code and web content

    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
    EG
    -0.26
    pet
    -0.26
    å¼ķåħ¥
    -0.26
    æĬ¥è®°èĢħ
    -0.26
    ]+"
    -0.25
    主è¦ģæľī
    -0.25
    ionate
    -0.25
    Pet
    -0.25
    ç´ļ
    -0.25
    ransition
    -0.24
    POSITIVE LOGITS
     later
    0.30
    Dll
    0.28
    以åIJİ
    0.27
    åIJĮç±»
    0.27
    later
    0.26
    dll
    0.25
    ä¿¡ç®±
    0.24
    heads
    0.24
    ınd
    0.24
    mor
    0.24
    Activations Density 69.000%

    No Known Activations