© 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. 63044
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    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
    ä¼ĺ
    -0.28
     доÑģÑĤ
    -0.26
    ì²´
    -0.25
    åĨħçļĦ
    -0.25
    ctic
    -0.24
    ä¸įæĺİ
    -0.24
    Abs
    -0.24
    .translate
    -0.24
    .dist
    -0.23
     equivalence
    -0.23
    POSITIVE LOGITS
    ients
    0.27
    为人
    0.26
    illac
    0.26
    lus
    0.25
    cripts
    0.25
    	CG
    0.24
    riterion
    0.24
    аÑĢам
    0.24
    aits
    0.24
    åĴĮæĶ¯æĮģ
    0.24
    Activations Density 17.632%

    No Known Activations