© 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. 14-TRANSCODER-HP
    7. 39888
    Prev
    Next
    INDEX
    Explanations

    grades and numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬åħ±èµĦæºIJ
    -0.29
    UBLE
    -0.27
    iked
    -0.26
    lingen
    -0.26
    æ±Ĺ
    -0.26
     irresistible
    -0.25
    ä½ıåĿĢ
    -0.25
    å¾®éĩı
    -0.25
     respected
    -0.25
     KE
    -0.24
    POSITIVE LOGITS
     reconciliation
    0.26
    ÑģÑĤÑĮ
    0.26
    çĵ®
    0.25
    .serialization
    0.24
    tam
    0.24
    ÉĶ
    0.24
    鬼
    0.23
     Suicide
    0.23
    èĤ¡æ°ij
    0.23
     ob
    0.23
    Activations Density 0.342%

    No Known Activations