© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107072
    Prev
    Next
    INDEX
    Explanations

    private

    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
    Negative Logits
    çĤ¹åĩ»æŁ¥çľĭ
    -0.28
     Dos
    -0.26
    æĢ§èĥ½
    -0.26
    ÑĢаг
    -0.25
    çļĦåħ·ä½ĵ
    -0.25
    éĩįè¦ģåĨħ容
    -0.25
    åī¯ä½ľçĶ¨
    -0.24
     Gluten
    -0.24
    åıĻäºĭ
    -0.24
     uniq
    -0.24
    POSITIVE LOGITS
     pen
    0.29
    lesh
    0.27
     compounded
    0.27
    ä¸ī级
    0.27
     birthdays
    0.26
     textbook
    0.26
    Share
    0.26
    aths
    0.25
     share
    0.25
    ASI
    0.25
    Activations Density 0.155%

    No Known Activations