© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62774
    Prev
    Next
    INDEX
    Explanations

    forward

    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
    Negative Logits
    irk
    -0.30
    abh
    -0.28
    补水
    -0.27
    CanBe
    -0.27
    ĵį
    -0.25
     Sty
    -0.25
    RIX
    -0.24
    ria
    -0.24
    毯
    -0.24
    ouns
    -0.24
    POSITIVE LOGITS
    /operator
    0.27
    -us
    0.27
     guys
    0.26
    è§ĦåĪĴ建设
    0.25
     analysed
    0.25
    åĽłä¸ºå¥¹
    0.25
     favourable
    0.25
    criptor
    0.25
    plans
    0.25
    centre
    0.25
    Activations Density 6.194%

    No Known Activations