© 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. 14-TRANSCODER-HP
    7. 40287
    Prev
    Next
    INDEX
    Explanations

    classical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¬Ŀ
    -0.27
    å®Ľ
    -0.26
    ĽĦ
    -0.26
     mapper
    -0.26
    adoo
    -0.26
    mapper
    -0.26
    æµĭç»ĺ
    -0.26
     oltre
    -0.25
    uos
    -0.25
     Mapper
    -0.24
    POSITIVE LOGITS
    款
    0.32
    EventListener
    0.28
    æĥħåĨµ
    0.26
    æĦŁ
    0.26
    ROME
    0.25
    tha
    0.25
    墨
    0.24
    irit
    0.24
    ordova
    0.24
    resden
    0.23
    Activations Density 3.094%

    No Known Activations