© 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. 56733
    Prev
    Next
    INDEX
    Explanations

    like

    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
    éĤ£ä½ł
    -0.27
    æļĩ
    -0.26
    Compilation
    -0.26
    lasting
    -0.26
    è´±
    -0.26
    éĹ®æĪij
    -0.26
    åij¨åħŃ
    -0.26
     lẫn
    -0.25
    让她
    -0.25
    éĹ®ä»ĸ
    -0.25
    POSITIVE LOGITS
     everyone
    0.35
     there
    0.33
     everybody
    0.30
    èĢģå¸Ī们
    0.30
    åѦçĶŁä»¬
    0.28
     maybe
    0.28
    everyone
    0.28
     There
    0.28
     nobody
    0.28
    æīĢæľīçļĦ
    0.28
    Activations Density 0.024%

    No Known Activations