© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23658
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èģĶ社
    -0.29
    çīĩåĪ»
    -0.27
    è¿ĻäºĽéĹ®é¢ĺ
    -0.27
    prep
    -0.26
    _cmos
    -0.25
    ç»Ĩç»Ĩ
    -0.25
    çĮ·
    -0.25
    odiac
    -0.25
    ä¾®
    -0.24
    好æĦŁ
    -0.24
    POSITIVE LOGITS
    åı¦ä¸Ģç§į
    0.35
    åı¦ä¸Ģ个
    0.35
    åħ¶ä»ĸçļĦ
    0.35
     another
    0.34
     other
    0.33
    Another
    0.30
    åħ¶ä»ĸ
    0.30
    another
    0.30
     alternatively
    0.29
     alternative
    0.29
    Activations Density 0.001%

    No Known Activations