© 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. 23071
    Prev
    Next
    INDEX
    Explanations

    Chemical elements/mining

    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
    orio
    -0.28
     percussion
    -0.27
    dere
    -0.27
    è¹´
    -0.26
    andering
    -0.26
    ħ§
    -0.25
    |i
    -0.25
    dead
    -0.25
    ATAL
    -0.25
    æīĵçIJĥ
    -0.24
    POSITIVE LOGITS
    çļĦåķĨåĵģ
    0.26
    è¡Įä¸ļä¸Ń
    0.26
    rzy
    0.26
    modity
    0.25
    èį·
    0.25
    è¡Įä¸ļ
    0.25
    éģĵ
    0.24
     commercially
    0.24
    Proceed
    0.24
    æĪļ
    0.24
    Activations Density 0.001%

    No Known Activations