© 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. 63226
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Miner
    -0.29
    Io
    -0.29
    tees
    -0.26
    è§ģè¯ģäºĨ
    -0.25
    '))->
    -0.25
     competitiveness
    -0.24
    udo
    -0.24
     affordability
    -0.24
    ween
    -0.23
    orio
    -0.23
    POSITIVE LOGITS
     temp
    0.28
    çĪĨ
    0.25
    åºĻ
    0.25
    ä¸įåıĹ
    0.25
     daddy
    0.25
     moments
    0.25
     TMP
    0.24
     momento
    0.24
    atur
    0.24
     tem
    0.24
    Activations Density 9.044%

    No Known Activations