© 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. 30-TRANSCODER-HP
    7. 96080
    Prev
    Next
    INDEX
    Explanations

    living

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LinkId
    -0.26
     backup
    -0.24
     bench
    -0.24
    оÑī
    -0.23
    chants
    -0.23
    arra
    -0.23
    decorators
    -0.23
    grades
    -0.23
    ICC
    -0.23
    Recovered
    -0.22
    POSITIVE LOGITS
     living
    1.73
    çĶŁæ´»
    1.49
    living
    1.45
    çĶŁæ´»çļĦ
    1.39
     Living
    1.37
     lives
    1.35
     live
    1.35
     lived
    1.34
    Living
    1.31
    æ´»
    1.31
    Activations Density 1.331%

    No Known Activations