© 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. 97855
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åºĶ该å¦Ĥä½ķ
    -0.26
    é«Ń
    -0.24
    å·¥ä¸ļä¼ģä¸ļ
    -0.23
    éĥ¢
    -0.23
    [src
    -0.23
    çļĦåľ°
    -0.23
    æľºä½ĵ
    -0.23
    mites
    -0.23
     visualize
    -0.22
    ä¸Ģè¾ĪåŃIJ
    -0.21
    POSITIVE LOGITS
    0.26
    ach
    0.26
     garbage
    0.23
    atham
    0.23
    cre
    0.23
    .
    0.22
    éļĨ
    0.22
    sts
    0.22
    avit
    0.21
    åIJĮç±»
    0.21
    Activations Density 0.410%

    No Known Activations

    This feature has no known activations.