© 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. 40399
    Prev
    Next
    INDEX
    Explanations

    Dickinson

    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
    	define
    -0.29
    bane
    -0.29
    berapa
    -0.25
    itest
    -0.25
     ÑģоÑģÑĤ
    -0.25
     завод
    -0.24
     ban
    -0.24
     scrim
    -0.24
     guarante
    -0.24
    å²ģ以ä¸ĭ
    -0.24
    POSITIVE LOGITS
     trickle
    0.27
    åıĺåĮĸ
    0.27
    pe
    0.25
    è®ĬåĮĸ
    0.24
    åĬ©åѦ
    0.24
    urbation
    0.24
    variation
    0.24
    ses
    0.23
    æĢ§ä»·æ¯Ķ
    0.23
    ms
    0.23
    Activations Density 0.046%

    No Known Activations