© 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. 25-TRANSCODER-HP
    7. 108268
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spots
    -0.28
     spot
    -0.27
    zos
    -0.26
    Cascade
    -0.26
    Locked
    -0.26
    .Down
    -0.26
     Weak
    -0.26
    orget
    -0.25
     Cay
    -0.25
     weak
    -0.25
    POSITIVE LOGITS
    åıij声
    0.32
    åĩºåĬ¨
    0.30
    ivist
    0.28
    ç«¿
    0.27
    singular
    0.27
    åĽºå®ļçļĦ
    0.26
    æĢ»æĶ¶åħ¥
    0.26
    æĸĩä½ĵ
    0.26
    主è¦ģçĶ¨äºİ
    0.26
    æľīå¾Ī大
    0.25
    Activations Density 0.895%

    No Known Activations