© 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. 64474
    Prev
    Next
    INDEX
    Explanations

    forms of "be"

    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
    ered
    -0.29
    IZER
    -0.28
    ured
    -0.27
    orte
    -0.26
    abled
    -0.26
    imat
    -0.26
    ToProps
    -0.25
    izer
    -0.25
    ful
    -0.25
    izador
    -0.25
    POSITIVE LOGITS
     Tiá»ģn
    0.26
    çĭ¬ä¸Ģ
    0.25
    starter
    0.25
    -heavy
    0.24
     salty
    0.24
     CONTRIBUTORS
    0.23
    带éĺŁ
    0.23
     needless
    0.23
    æģ£
    0.23
    /jav
    0.23
    Activations Density 17.260%

    No Known Activations