© 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. 107218
    Prev
    Next
    INDEX
    Explanations

    statistical methods and data analysis

    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
    olls
    -0.29
    umd
    -0.28
    opleft
    -0.27
    mj
    -0.26
    çIJĨ论
    -0.26
    åıĸè¯ģ
    -0.25
     Vacuum
    -0.25
     Phys
    -0.25
    çĶµå·¥
    -0.25
     Doctrine
    -0.25
    POSITIVE LOGITS
    åĽŀå½Ĵ
    0.32
    ãĥ¬ãĤ¹ãĥĪ
    0.32
     setHidden
    0.29
    ÑģеÑĤ
    0.28
    ç¨Ģ
    0.28
     regress
    0.27
    Principal
    0.27
     networks
    0.26
    asi
    0.26
    iesta
    0.26
    Activations Density 1.444%

    No Known Activations