© 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. 8350
    Prev
    Next
    INDEX
    Explanations

    web content with counts

    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
     crowds
    -0.31
    éĢł
    -0.29
     crowd
    -0.29
     Crowd
    -0.28
    mouth
    -0.26
    éĹ¾
    -0.25
    æ±Łæ¹ĸ
    -0.25
    croft
    -0.25
    è®°
    -0.24
     carnival
    -0.24
    POSITIVE LOGITS
    omas
    0.28
    idis
    0.27
    æľīä¸ĢçĤ¹
    0.26
    åĪĨ管
    0.26
    ä¸ĢçĤ¹
    0.24
    ä¸ĢéĤĬ
    0.24
     hel
    0.23
    æĿ¡
    0.23
    è¿Ļä¸ĢçĤ¹
    0.23
    FULL
    0.23
    Activations Density 0.001%

    No Known Activations