© 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. 42532
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    ⼦
    -0.28
    åŃĻ
    -0.27
     great
    -0.27
    -s
    -0.26
    ãĥķãĤ¡
    -0.26
     ÐijолÑĮÑĪ
    -0.25
     sle
    -0.25
    trace
    -0.25
    æİ¢
    -0.25
     Accord
    -0.24
    POSITIVE LOGITS
    rai
    0.27
    hare
    0.26
    åıijå±ķæł¼å±Ģ
    0.24
    çĽĴ
    0.24
    失èIJ½
    0.24
    óa
    0.24
    inium
    0.24
    ropic
    0.24
     OE
    0.23
    ä»ģ
    0.23
    Activations Density 0.007%

    No Known Activations