© 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. 87888
    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_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
    ãĢģ
    -0.31
    ruc
    -0.29
    æĪĸæĺ¯
    -0.28
    以åıĬåħ¶ä»ĸ
    -0.27
     Intr
    -0.27
     and
    -0.27
     intr
    -0.26
    人åıĤ
    -0.26
    åĴĮåħ¶ä»ĸ
    -0.26
    pace
    -0.26
    POSITIVE LOGITS
    çģ«çĦ°
    0.26
    AYOUT
    0.26
    è§ģæķĪ
    0.25
    æĢĽ
    0.24
    <tag
    0.24
    çĽ¸ä¿¡
    0.24
    tem
    0.24
     hiá»ĩu
    0.24
    .Fl
    0.24
    èĢĮåĩº
    0.24
    Activations Density 0.009%

    No Known Activations