© 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. 96016
    Prev
    Next
    INDEX
    Explanations

    code and research

    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
    reinterpret
    -0.28
    åij½
    -0.27
    ilig
    -0.26
    éĿĻæĢģ
    -0.26
    éĩįçĤ¹
    -0.25
    é£ķ
    -0.25
    Ip
    -0.24
     Ãĸzellik
    -0.23
    æłħ
    -0.23
    spark
    -0.23
    POSITIVE LOGITS
    éĶIJ
    0.30
    æľªæĪIJ
    0.29
    å¼ķæµģ
    0.28
     pa
    0.28
    å¦Ĩ
    0.27
     rolls
    0.27
    اظ
    0.27
    èħ¹
    0.26
     flows
    0.26
     ASC
    0.26
    Activations Density 0.883%

    No Known Activations