© 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. 112489
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment

    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
    ä¼ļä¸įä¼ļ
    -0.26
    èĥ½ä¸įèĥ½
    -0.26
    ining
    -0.26
    解éĩĬ
    -0.25
    æªIJ
    -0.25
    è°ħ
    -0.25
    说ä»Ģä¹Ī
    -0.24
    å·´æĸ¯
    -0.24
     dÄ±ÅŁÄ±nda
    -0.24
    æľī没æľī
    -0.24
    POSITIVE LOGITS
    'er
    0.26
     trains
    0.25
    æľĭ
    0.24
    adera
    0.24
    .Serve
    0.24
     goodwill
    0.24
     trainer
    0.24
    .Companion
    0.24
     Coroutine
    0.23
    cellent
    0.23
    Activations Density 0.040%

    No Known Activations