© 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. 96101
    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
    çĤ¹åĩ»æŁ¥çľĭ
    -0.28
     UIApplication
    -0.28
     Pump
    -0.28
    è¿ĩåİ»
    -0.27
     dém
    -0.26
    nez
    -0.26
    æ´¾
    -0.25
    æīĵçIJĥ
    -0.25
    game
    -0.25
    ðŁijģ
    -0.24
    POSITIVE LOGITS
    åĴĮå¹³
    0.32
     peace
    0.31
    isko
    0.30
    utos
    0.26
    cale
    0.26
     hu
    0.26
     scale
    0.26
     Republic
    0.26
     vectors
    0.25
     republic
    0.25
    Activations Density 0.003%

    No Known Activations