© 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. 12-TRANSCODER-HP
    7. 23064
    Prev
    Next
    INDEX
    Explanations

    supervision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uess
    -0.28
    åľ»
    -0.27
    ysis
    -0.27
     Dissertation
    -0.25
     stad
    -0.25
    мÑı
    -0.25
    iben
    -0.25
    SCI
    -0.24
    æĪ³
    -0.24
    IDGE
    -0.23
    POSITIVE LOGITS
    åĮº
    0.32
    羣æŃ£çļĦ
    0.30
    åľ°å¸¦
    0.28
    å¤ĸåĮħ
    0.27
     trans
    0.26
    åĮºåĨħ
    0.26
    sembling
    0.25
    ae
    0.25
     regenerated
    0.25
    ä¸ĸçķĮçļĦ
    0.25
    Activations Density 0.066%

    No Known Activations