© 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. 130482
    Prev
    Next
    INDEX
    Explanations

    as

    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
    à¹ģà¸Ī
    -0.26
    Flexible
    -0.26
     balances
    -0.26
     Flexible
    -0.25
    esar
    -0.25
    andReturn
    -0.25
    lessly
    -0.25
     AÄŁustos
    -0.25
    æĢ§å¼º
    -0.24
    ILITY
    -0.24
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.27
    NavController
    0.27
    @\
    0.26
    weep
    0.26
    ~
    0.25
    éģĹ
    0.25
    åĪĿ次
    0.25
     collective
    0.25
    ipe
    0.25
     annual
    0.24
    Activations Density 6.211%

    No Known Activations