© 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. 129871
    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
     soon
    -0.24
    -Headers
    -0.23
    头
    -0.23
    ssc
    -0.23
    æ³¢çī¹
    -0.23
    lic
    -0.23
     imprisonment
    -0.23
    æ§ģ
    -0.22
     rip
    -0.22
     JNICALL
    -0.22
    POSITIVE LOGITS
    è¦ģèĢĥèĻij
    0.26
     retrospect
    0.26
     deque
    0.25
    onder
    0.25
    ovie
    0.25
    ást
    0.25
     hindsight
    0.24
     Phụ
    0.24
    cape
    0.23
     Prim
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.