© 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. 130704
    Prev
    Next
    INDEX
    Explanations

    Random short texts

    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
    ä¸ļåĬ¡
    -0.27
     gains
    -0.27
     Ngoại
    -0.26
    _singleton
    -0.25
    един
    -0.25
     singleton
    -0.25
    rape
    -0.25
    uge
    -0.25
     Concat
    -0.25
    æŃ£å¼ı
    -0.24
    POSITIVE LOGITS
     emptied
    0.29
    removed
    0.29
    warts
    0.28
    èĥ½æī¾åĪ°
    0.27
    解æķ£
    0.27
     regression
    0.26
    âĢ¦↵↵↵↵
    0.26
    isan
    0.26
     removed
    0.25
     removable
    0.25
    Activations Density 0.002%

    No Known Activations