© 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. 130335
    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
    èĢģ人
    -0.29
    SE
    -0.25
    åħħå®ŀ
    -0.23
     Äijá»Ŀi
    -0.23
    åĩºè®©
    -0.23
    нÑĥл
    -0.22
    åıijæĮ¥äºĨ
    -0.22
    大åıĶ
    -0.22
    chet
    -0.22
     Bloody
    -0.22
    POSITIVE LOGITS
    æĶ¿æ³ķ
    0.25
    éļĻ
    0.24
    æ°ij主çĶŁæ´»
    0.24
     tats
    0.24
    pective
    0.24
    å½¢åĬ¿
    0.24
     |=
    0.23
     oo
    0.23
    ãĥīãĥ¬ãĤ¹
    0.23
    "|
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.