© 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. 31-TRANSCODER-HP
    7. 19263
    Prev
    Next
    INDEX
    Explanations

    and or comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     child
    -0.41
     ÑĢебен
    -0.36
     Child
    -0.36
    å°ıåŃ©
    -0.35
    åĦ¿ç«¥
    -0.35
    -child
    -0.34
    å°ıåĦ¿
    -0.33
    child
    -0.33
    åĦ¿åŃIJ
    -0.33
    åŃ©åŃIJ
    -0.32
    POSITIVE LOGITS
    gran
    0.35
     animals
    0.30
     schools
    0.28
     families
    0.28
     teachers
    0.28
    åıijæĸĩ
    0.27
    Grand
    0.27
     grand
    0.27
    æī¹
    0.27
    éĻIJ度
    0.26
    Activations Density 0.010%

    No Known Activations