© 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. 30-TRANSCODER-HP
    7. 96036
    Prev
    Next
    INDEX
    Explanations

    world

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ance
    -0.28
     comm
    -0.28
    çŃĶ
    -0.28
    ase
    -0.28
    稷
    -0.27
    umb
    -0.25
     freely
    -0.25
    åIJĪ
    -0.24
    comm
    -0.24
    arda
    -0.24
    POSITIVE LOGITS
    cycle
    0.30
    æľīè¿Ļæł·çļĦ
    0.28
    cycles
    0.28
    -scalable
    0.27
     getClass
    0.27
    _locations
    0.26
    éĿ¢ç§¯
    0.26
    èĮ¸
    0.26
    -class
    0.26
    çĶµéĩı
    0.26
    Activations Density 0.022%

    No Known Activations