© 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. 9397
    Prev
    Next
    INDEX
    Explanations

    cost

    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
     Lage
    -0.32
    é¢ī
    -0.27
     Cong
    -0.26
    ulg
    -0.26
    ç¼¢
    -0.25
    æİ
    -0.24
    宫
    -0.24
     gy
    -0.24
     geben
    -0.24
    ä½ĵæ£Ģ
    -0.23
    POSITIVE LOGITS
    æĪIJæľ¬
    0.67
    éĹ¨æ§Ľ
    0.65
     cost
    0.57
    çļĦæĪIJæľ¬
    0.50
    cost
    0.50
    ãĤ³ãĤ¹ãĥĪ
    0.50
     costs
    0.46
     barrier
    0.46
     COST
    0.45
     Cost
    0.45
    Activations Density 0.003%

    No Known Activations