© 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. 8390
    Prev
    Next
    INDEX
    Explanations

    patents/technical writing

    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
    é¢Ļ
    -0.28
    èIJ¥åĪ©
    -0.26
    orsi
    -0.26
    |i
    -0.26
    nk
    -0.25
    åĪºæ¿Ģ
    -0.25
    -middle
    -0.25
    æ¯į
    -0.24
    åįİå°Ķ
    -0.24
    ulate
    -0.24
    POSITIVE LOGITS
    adget
    0.27
    eree
    0.27
    åħ³éĶ®æĬĢæľ¯
    0.27
    缺çĤ¹
    0.26
    æĺ¯éĿŀ
    0.26
    åIJĪæł¼
    0.26
     efficiencies
    0.25
     Ru
    0.25
     acceptable
    0.25
    ï¬ĥ
    0.25
    Activations Density 0.026%

    No Known Activations