© 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. 39846
    Prev
    Next
    INDEX
    Explanations

    Products, selling, installation

    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
    æĵħ
    -0.28
     implied
    -0.27
    æ°¨éħ¸
    -0.27
    illis
    -0.26
    ç«ĻçĿĢ
    -0.26
    ä¸Ģå¤Ħ
    -0.26
    ernals
    -0.25
    ä¸īè§Ĵ
    -0.25
    åIJİåı°
    -0.25
    adar
    -0.24
    POSITIVE LOGITS
    èµĽ
    0.27
     redeem
    0.26
    kind
    0.25
    çĽĺ
    0.25
    æŃ£çīĪ
    0.25
    mach
    0.25
     redeemed
    0.25
     Redistribution
    0.25
     discarded
    0.24
    Kind
    0.24
    Activations Density 1.111%

    No Known Activations