© 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. 27-TRANSCODER-HP
    7. 8306
    Prev
    Next
    INDEX
    Explanations

    memory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    身
    -0.27
    Ĩµ
    -0.27
    =sys
    -0.27
     Universal
    -0.26
     altogether
    -0.26
    WindowText
    -0.26
     without
    -0.25
    åĨį说
    -0.25
     без
    -0.25
    jang
    -0.25
    POSITIVE LOGITS
    æĺİæĺ¾
    0.29
    æįŁå¤±
    0.28
    æ¼Ĥ
    0.27
    æ³¢åĬ¨
    0.27
    éĹ®é¢ĺæĺ¯
    0.26
    ibble
    0.26
     DAMAGE
    0.25
     difficulty
    0.25
     difficulties
    0.25
    æĺİæĺ¾çļĦ
    0.25
    Activations Density 0.004%

    No Known Activations