© 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. 33-TRANSCODER-HP
    7. 53740
    Prev
    Next
    INDEX
    Explanations

    head

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dai
    -0.30
    sein
    -0.30
     disemb
    -0.27
    å¹³åı°ä¸Ĭ
    -0.27
    anism
    -0.26
    社ä¼ļ
    -0.25
    antes
    -0.25
    éĹ»
    -0.25
    ker
    -0.25
    SO
    -0.25
    POSITIVE LOGITS
     heads
    0.36
     Head
    0.34
     head
    0.31
    Head
    0.30
    heads
    0.30
    头
    0.30
    uros
    0.28
    tu
    0.26
    EAR
    0.26
     mix
    0.25
    Activations Density 0.005%

    No Known Activations