© 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. 14-TRANSCODER-HP
    7. 41635
    Prev
    Next
    INDEX
    Explanations

    Data analysis/significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¶Ī
    -0.29
    elim
    -0.28
    ilage
    -0.28
    Elim
    -0.28
    _elim
    -0.27
    ilan
    -0.26
    antes
    -0.25
     Castillo
    -0.24
     htmlentities
    -0.24
    çŁŃ
    -0.24
    POSITIVE LOGITS
    æµĭè¯Ħ
    0.28
    cek
    0.28
     mou
    0.27
    rijk
    0.27
    æĬĬä»ĸ
    0.26
    (EFFECT
    0.26
    çĿ¹
    0.26
    èĩªçĦ¶
    0.25
    产çī©
    0.25
    (++
    0.25
    Activations Density 0.112%

    No Known Activations