© 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. 14-TRANSCODER-HP
    7. 41704
    Prev
    Next
    INDEX
    Explanations

    Mass spectrometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stor
    -0.28
    è¦ģç´§
    -0.27
    llib
    -0.26
    duÄŁ
    -0.26
    ableObject
    -0.25
    æįĥ
    -0.25
     thereby
    -0.25
    WithOptions
    -0.24
    azy
    -0.24
    GOP
    -0.23
    POSITIVE LOGITS
    /rec
    0.28
    å°¼æĸ¯
    0.26
     recurrence
    0.26
    ÑĢеÑģ
    0.26
    缼è¡Į
    0.25
     verm
    0.25
    åħ¨éĿ¢åıijå±ķ
    0.25
     Placement
    0.25
    èIJ½åĪ°å®ŀå¤Ħ
    0.23
    bul
    0.23
    Activations Density 1.104%

    No Known Activations