© 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. 129295
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
     Whereas
    -0.27
    ockets
    -0.25
    æĸ¼
    -0.25
    ÑĢова
    -0.25
    以为
    -0.24
    ceased
    -0.23
    èĩ³æĸ¼
    -0.23
    ãĥªãĥ³ãĤ°
    -0.23
    ä¸īä½į
    -0.23
     note
    -0.23
    POSITIVE LOGITS
    quals
    0.28
    æĬķ
    0.28
    çļĦäºĭæĥħ
    0.27
    ahir
    0.27
    enerative
    0.24
    -aff
    0.24
    åįıè°ĥåıijå±ķ
    0.24
    夷
    0.24
     greatness
    0.23
    亥
    0.23
    Activations Density 12.189%

    No Known Activations