© 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. 57411
    Prev
    Next
    INDEX
    Explanations

    say the ending -ular

    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
    erea
    -0.27
    igin
    -0.27
    ç²Ĺç³Ļ
    -0.26
    åĮħ
    -0.26
    ä¼Ĭæĭī
    -0.25
     Bind
    -0.25
    åį·
    -0.25
    tet
    -0.24
    æĭ¼åij½
    -0.24
    æ°¨éħ¸
    -0.24
    POSITIVE LOGITS
    ainless
    0.28
    飧
    0.27
    佩æĪ´
    0.26
    æŀIJ
    0.25
    è¡£
    0.25
    brace
    0.25
    athy
    0.25
    eldorf
    0.25
    oves
    0.25
    anean
    0.24
    Activations Density 0.026%

    No Known Activations