© 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. 95563
    Prev
    Next
    INDEX
    Explanations

    dictionary

    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
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.26
    Å©ng
    -0.26
    æĿ¡ä»¶
    -0.26
     Conditions
    -0.26
    quired
    -0.26
    -BEGIN
    -0.26
    滩
    -0.25
    èĭįçĻ½
    -0.25
    aktu
    -0.25
    åĮĸ
    -0.24
    POSITIVE LOGITS
    -final
    0.29
     lex
    0.29
     compiled
    0.28
    Containing
    0.28
     compile
    0.28
    æ¹
    0.27
     dictionary
    0.27
    çIJ¼
    0.27
     comp
    0.27
    çĵ
    0.27
    Activations Density 0.112%

    No Known Activations