© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56547
    Prev
    Next
    INDEX
    Explanations

    Title/name mentions

    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
    Negative Logits
     scrim
    -0.28
    enance
    -0.28
    榻
    -0.26
    æĿ¥çĶµ
    -0.25
     verdict
    -0.25
    å¹ķ
    -0.24
    е
    -0.24
    绸
    -0.23
    ennon
    -0.23
     pulp
    -0.23
    POSITIVE LOGITS
    çł´
    0.30
    åİĨåı²æĢ§
    0.27
    è£ħ
    0.27
    oge
    0.26
    è¯ģåĪ¸äº¤æĺĵ
    0.26
     Fay
    0.25
     masses
    0.24
    å·¥ç¨ĭè´¨éĩı
    0.24
    åħļçļĦé¢Ĩ导
    0.24
    eson
    0.23
    Activations Density 0.002%

    No Known Activations