© 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. 23433
    Prev
    Next
    INDEX
    Explanations

    Comparisons and degrees

    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
    代åĬŀ
    -0.27
    åĽ¾çĶ»
    -0.26
    ordination
    -0.25
    ties
    -0.25
    erten
    -0.25
    å°ijéĩı
    -0.25
    	ON
    -0.25
    æ¢Ŀ
    -0.24
    alphabet
    -0.24
    /DD
    -0.23
    POSITIVE LOGITS
    Prev
    0.27
    ply
    0.27
    pon
    0.27
     reversing
    0.27
    aders
    0.27
     Trad
    0.27
    prev
    0.27
     left
    0.26
     ups
    0.26
    anta
    0.26
    Activations Density 0.007%

    No Known Activations