© 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. 63616
    Prev
    Next
    INDEX
    Explanations

    Scientific abstracts

    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
     Sang
    -0.27
    èĪ±
    -0.27
    æķĪåĬĽ
    -0.26
    è¿Ļæł·æīįèĥ½
    -0.25
    dent
    -0.25
     sting
    -0.25
     sang
    -0.25
    æŀģåĬĽ
    -0.25
     lyr
    -0.24
    æģ¹
    -0.24
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.29
    åĪĩ
    0.28
    riding
    0.26
     Implements
    0.26
    -ce
    0.25
     Sounds
    0.25
     hanging
    0.24
    ä¸Ģæľ¬ä¹¦
    0.24
    "profile
    0.24
    sector
    0.24
    Activations Density 34.985%

    No Known Activations