© 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. 14-TRANSCODER-HP
    7. 41141
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous computer/math/law snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨åħ¨çIJĥ
    -0.27
    ampoo
    -0.26
    å¹²æű
    -0.25
     unf
    -0.25
    .scope
    -0.24
    æŀ¯çĩ¥
    -0.24
    á¹ĸ
    -0.24
     blindly
    -0.24
    ä»Ļ女
    -0.24
    éĢĿä¸ĸ
    -0.23
    POSITIVE LOGITS
    Brown
    0.27
     community
    0.26
     communities
    0.25
     counters
    0.25
     memory
    0.25
    ether
    0.25
    社åĮº
    0.24
    áĢĸ
    0.24
     fif
    0.24
     programming
    0.24
    Activations Density 1.818%

    No Known Activations