© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 53
    Prev
    Next
    INDEX
    Explanations

    mayor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·©åĽº
    -0.27
    ems
    -0.26
    IEW
    -0.26
    quirrel
    -0.26
    iel
    -0.26
    piar
    -0.25
    ä½ĵä¼ļ
    -0.25
    em
    -0.24
     bri
    -0.24
     Báo
    -0.23
    POSITIVE LOGITS
     depressive
    0.26
    ãģ¾ãģĹãģ¦
    0.26
     Primer
    0.26
    -major
    0.25
     обÑĢаÑīа
    0.25
     minority
    0.25
     Minority
    0.24
    Tube
    0.24
     major
    0.24
     Depression
    0.24
    Activations Density 0.138%

    No Known Activations