© 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. 24-TRANSCODER-HP
    7. 151354
    Prev
    Next
    INDEX
    Explanations

    Rep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mature
    -0.29
     brethren
    -0.28
     distinguished
    -0.27
     shares
    -0.27
     frat
    -0.27
    天çĶŁ
    -0.26
     uniquely
    -0.26
    æĺĤ
    -0.26
     phoenix
    -0.26
    rios
    -0.25
    POSITIVE LOGITS
    éĨī
    0.32
    èħIJè´¥
    0.32
     cheating
    0.30
    娼
    0.30
     Dirt
    0.29
    whatever
    0.28
    Reality
    0.28
    âĪ
    0.28
    èĩªç§ģ
    0.28
    à¹ģ
    0.27
    Activations Density 0.957%

    No Known Activations