© 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. 12-TRANSCODER-HP
    7. 23009
    Prev
    Next
    INDEX
    Explanations

    Coding and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QS
    -0.27
    èĥ¡åŃIJ
    -0.26
    æľįä»İ
    -0.25
    TRS
    -0.25
    usal
    -0.25
    寿
    -0.25
    åij¼åĴĮ
    -0.24
    asma
    -0.24
    -boy
    -0.24
    antes
    -0.24
    POSITIVE LOGITS
    çī¹å®ļ
    0.30
    çļĦçĭ¬çī¹
    0.30
    imet
    0.29
     Astroph
    0.27
    itat
    0.26
    onet
    0.25
     specific
    0.25
    alytics
    0.24
    iaux
    0.24
     Mess
    0.24
    Activations Density 0.006%

    No Known Activations