© 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. 107568
    Prev
    Next
    INDEX
    Explanations

    Adjectives ending in "ive"/"ative"

    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
    vak
    -0.33
    ington
    -0.28
     Existing
    -0.27
    jourd
    -0.27
    edImage
    -0.26
     Loving
    -0.26
     NSK
    -0.25
    ![↵
    -0.24
    edException
    -0.24
     ProductService
    -0.24
    POSITIVE LOGITS
    rys
    0.29
     amounts
    0.29
    rist
    0.28
     cleaned
    0.28
     keys
    0.28
    åİŁåĽłä¹ĭä¸Ģ
    0.27
    vent
    0.27
     sets
    0.27
    leaning
    0.27
     measures
    0.26
    Activations Density 24.931%

    No Known Activations