© 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. 30-TRANSCODER-HP
    7. 97021
    Prev
    Next
    INDEX
    Explanations

    b

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zos
    -0.27
    iam
    -0.25
     process
    -0.25
    çŃ
    -0.25
    zo
    -0.25
     black
    -0.25
    纸
    -0.25
    gó
    -0.24
     Voy
    -0.24
    å°±è¿Ļä¹Ī
    -0.24
    POSITIVE LOGITS
    ÑĨиÑĤ
    0.31
    åİĭ
    0.28
    æłĵ
    0.28
    ught
    0.27
    笼
    0.26
    otion
    0.26
    andin
    0.26
    une
    0.26
    代çIJĨ
    0.25
     Lun
    0.24
    Activations Density 0.002%

    No Known Activations