© 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. 20-TRANSCODER-HP
    7. 142273
    Prev
    Next
    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustom
    -0.31
    åħ¶æ¬¡æĺ¯
    -0.30
    åĬłä»¥
    -0.28
    è¿ĺæľīä¸Ģ个
    -0.28
    çĻ½éĵ¶
    -0.27
    æĢ»æĶ¶åħ¥
    -0.26
     seg
    -0.25
     infancy
    -0.25
     Mechanical
    -0.25
    Õ®
    -0.24
    POSITIVE LOGITS
    -ph
    0.27
    æ´Ĵ
    0.26
     ÑĤÑĢ
    0.26
    ï½IJ
    0.24
    ivr
    0.23
    ERO
    0.23
    uria
    0.23
    Æ°
    0.23
    çłģ头
    0.23
    KEN
    0.23
    Activations Density 64.212%

    No Known Activations