© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150240
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    绾
    -0.31
    Prob
    -0.27
    istique
    -0.27
    ares
    -0.26
    éŁ³
    -0.25
     suppose
    -0.25
     commissions
    -0.25
    gÅĤ
    -0.25
    åĩłçİĩ
    -0.25
    顾客
    -0.25
    POSITIVE LOGITS
    archy
    0.26
    pliers
    0.26
    åijĹ
    0.26
    æĸ°ç¯ĩç«ł
    0.26
    ä¸Ģ页
    0.25
     spacing
    0.25
    çĭ¬è§Ĵåħ½
    0.25
    OfYear
    0.25
    WithMany
    0.25
    é£İåı£
    0.25
    Activations Density 0.222%

    No Known Activations