© 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. 8168
    Prev
    Next
    INDEX
    Explanations

    foreign or place names

    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
    ediator
    -0.34
    ailles
    -0.28
    æĦıåIJij
    -0.28
    ailer
    -0.26
    æīĺ管
    -0.26
    å¤ĸæı´
    -0.25
    correct
    -0.25
     PE
    -0.25
    ail
    -0.25
    å½±ä¸ļ
    -0.24
    POSITIVE LOGITS
    æľ¬åľ°
    0.32
     locally
    0.31
    ccak
    0.28
    иÑĪ
    0.28
    å§Ķç»Ħç»ĩ
    0.28
    游
    0.27
     regional
    0.27
     reshape
    0.27
     region
    0.26
     localhost
    0.26
    Activations Density 0.002%

    No Known Activations