© 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. 63674
    Prev
    Next
    INDEX
    Explanations

    source

    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
     lique
    -0.26
     stakes
    -0.26
    åıĮèħ¿
    -0.25
    rops
    -0.24
     зан
    -0.24
     Internet
    -0.23
     posi
    -0.23
    Party
    -0.23
    -party
    -0.23
    éĻĦ
    -0.23
    POSITIVE LOGITS
    åIJĮç±»
    0.30
    ilha
    0.30
    å§Ĭ妹
    0.30
    ä¸Ģç±»
    0.29
    eya
    0.25
     proud
    0.25
    equiv
    0.25
    eba
    0.25
     counterparts
    0.25
    PM
    0.24
    Activations Density 0.595%

    No Known Activations