© 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. 32-TRANSCODER-HP
    7. 42536
    Prev
    Next
    INDEX
    Explanations

    Technical/formal language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     performance
    -0.34
     háºŃu
    -0.31
    Performance
    -0.28
    表æ¼Ķ
    -0.28
    æĢ»éĺŁ
    -0.28
     Performance
    -0.26
    elm
    -0.26
    performance
    -0.25
    avo
    -0.25
    æĶ¯çIJĥéĺŁ
    -0.25
    POSITIVE LOGITS
    åºķ
    0.30
    rog
    0.29
     Amit
    0.27
     getClient
    0.27
    rox
    0.26
    noc
    0.24
    imm
    0.24
    ä½ľæģ¯
    0.24
    åŁŁ
    0.24
    .Activity
    0.23
    Activations Density 0.000%

    No Known Activations