© 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. 27-TRANSCODER-HP
    7. 58211
    Prev
    Next
    INDEX
    Explanations

    recycling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OC
    -0.30
    æľīæĦı
    -0.27
    ½æķ°
    -0.27
    oci
    -0.26
    æĵį纵
    -0.25
    æ³¢çī¹
    -0.25
    奥è¿IJä¼ļ
    -0.25
    èĴĤ
    -0.25
    æķħæĦı
    -0.25
     horizontally
    -0.24
    POSITIVE LOGITS
    SRC
    0.28
    allon
    0.26
    egin
    0.26
    -return
    0.25
    ENDER
    0.25
    {return
    0.25
    ahead
    0.25
    InitialState
    0.24
     plates
    0.24
    @return
    0.24
    Activations Density 0.005%

    No Known Activations