© 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. 22-TRANSCODER-HP
    7. 98695
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įéĶĻ
    -0.30
    åıĹçĽĬ
    -0.28
    obile
    -0.27
     pong
    -0.25
     Mayer
    -0.25
     MADE
    -0.24
    @foreach
    -0.24
    èĪĴæľį
    -0.24
    æ£ĭ
    -0.24
    çļĦæĥ³æ³ķ
    -0.23
    POSITIVE LOGITS
    åı£å¾Ħ
    0.31
    çĻĥ
    0.27
    æįŁä¼¤
    0.27
    æ¢Ĩ
    0.26
    ä¼łéĢĴ
    0.25
    æĢ§æĦŁ
    0.25
    æĹĹèĪ°
    0.25
     News
    0.24
    æł¹æºIJ
    0.24
    Page
    0.24
    Activations Density 0.018%

    No Known Activations