© 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. 95464
    Prev
    Next
    INDEX
    Explanations

    concept

    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
    imuth
    -0.29
    uling
    -0.27
    éĢĤ
    -0.27
    zend
    -0.27
    æѤäºĭ
    -0.26
    ä¸Ģç¯ĩæĸĩç«ł
    -0.26
    =title
    -0.25
    失
    -0.25
    [method
    -0.25
    à¸Ĺะ
    -0.25
    POSITIVE LOGITS
     concept
    1.05
    æ¦Ĥ念
    1.03
     Concept
    1.00
    Concept
    0.99
    concept
    0.98
     concepts
    0.96
     Concepts
    0.87
     conception
    0.82
     conceptual
    0.82
    çļĦæ¦Ĥ念
    0.81
    Activations Density 0.917%

    No Known Activations