© 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. 20-TRANSCODER-HP
    7. 130619
    Prev
    Next
    INDEX
    Explanations

    negative life events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJ¬çĿĢ
    -0.27
    çľĭäºĨä¸Ģ
    -0.26
     cer
    -0.26
    otyping
    -0.26
    erval
    -0.26
    çļĦçĭ¬çī¹
    -0.26
    Taken
    -0.25
     fragmentation
    -0.25
    æĶ¾å¤§
    -0.24
    æĥ³åĪ°äºĨ
    -0.24
    POSITIVE LOGITS
    IFI
    0.28
    åı£æ°Ķ
    0.25
    ä¹ĭä¸Ģ
    0.25
    å°ij
    0.24
    åijĬ
    0.24
    budget
    0.24
     |
    0.24
    åĬŁ
    0.24
    ities
    0.24
    FLICT
    0.24
    Activations Density 9.225%

    No Known Activations