© 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. 129372
    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
    ä¸Ģæľµ
    -0.26
    人å¿ĥ
    -0.26
    .Serve
    -0.25
    shall
    -0.25
    rape
    -0.24
    Thread
    -0.24
    éĤ£ä»½
    -0.24
    æī¿è®¤
    -0.24
    è´¢æĬ¥
    -0.23
    å±
    -0.23
    POSITIVE LOGITS
    equalTo
    0.28
     scaled
    0.27
     Horn
    0.27
     dear
    0.27
    BIND
    0.25
    EGIN
    0.24
    план
    0.23
     definite
    0.23
     Cair
    0.23
    æ¯Ķãģ¹
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.