© 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. 24-TRANSCODER-HP
    7. 150237
    Prev
    Next
    INDEX
    Explanations

    including

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿİ
    -0.28
     popular
    -0.26
     invoked
    -0.26
    -hit
    -0.26
     particular
    -0.26
    åı©
    -0.25
    ILT
    -0.25
    -track
    -0.25
    æµģè¡ĮçļĦ
    -0.24
     poll
    -0.24
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.27
    顾
    0.26
     Proud
    0.26
    NIC
    0.25
    adero
    0.25
    ãģĹãģķ
    0.24
    sons
    0.24
    欺è¯Ī
    0.24
    iez
    0.23
    enza
    0.23
    Activations Density 0.215%

    No Known Activations