© 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. 96173
    Prev
    Next
    INDEX
    Explanations

    Queens

    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
     semiclass
    -0.28
     folk
    -0.26
    minster
    -0.25
     Beats
    -0.25
    umpt
    -0.25
    folk
    -0.24
    ç»ıæµİ社ä¼ļ
    -0.24
    å¾Ĺ天
    -0.24
    okes
    -0.24
    æĶĺ
    -0.23
    POSITIVE LOGITS
    itr
    0.28
     only
    0.26
    大åѦ
    0.26
    åıª
    0.26
    ngle
    0.25
    æµģåĬ¨æĢ§
    0.25
    åĿIJ
    0.25
    LAND
    0.24
    åıªæľī
    0.24
     Thread
    0.24
    Activations Density 0.005%

    No Known Activations