© 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. 112721
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    idle
    -0.27
     entitled
    -0.27
     consolidated
    -0.27
     research
    -0.26
     emb
    -0.26
     Gift
    -0.26
    heet
    -0.25
     End
    -0.25
     Research
    -0.25
     Aud
    -0.24
    POSITIVE LOGITS
    éĺ´å½±
    0.28
    éĢĨ
    0.28
    blogs
    0.25
    ä¸ªå·¥ä½ľ
    0.25
    -match
    0.25
    çĹĤ
    0.25
    åĮ¹éħį
    0.25
    å§ļæĺİ
    0.24
    æľĭåıĭ们
    0.24
    严åİī
    0.24
    Activations Density 0.054%

    No Known Activations