© 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. 25352
    Prev
    Next
    INDEX
    Explanations

    licensed

    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
    heroes
    -0.28
    (super
    -0.27
     ceilings
    -0.27
     originals
    -0.26
    æĸ¹ãģ¯
    -0.26
    æĬķèµĦé¡¹çĽ®
    -0.25
    ÙĬÙĬÙĨ
    -0.25
     ÑħозÑıйÑģÑĤв
    -0.25
     nurs
    -0.25
    ãģļãģ«
    -0.25
    POSITIVE LOGITS
    sym
    0.29
    åİ»äºĨ
    0.27
    itol
    0.27
    pline
    0.26
    åŀĤ
    0.25
    åı¦ä¸Ģä½į
    0.25
    åĨĻçĿĢ
    0.24
    hop
    0.23
    æĶ¾
    0.23
    åħħå®ŀ
    0.23
    Activations Density 0.155%

    No Known Activations