© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 172
    Prev
    Next
    INDEX
    Explanations

    collision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplan
    -0.25
    æ½ĩ
    -0.25
     recoil
    -0.24
    æ¥ŀ
    -0.24
    âĢ³
    -0.24
    ä¾Ľå¤§å®¶
    -0.24
    æĸ°éĻĪ
    -0.23
    langle
    -0.23
    æĸ°åĮº
    -0.22
     puis
    -0.22
    POSITIVE LOGITS
    åĽ½åĨħå¸Ĥåľº
    0.27
    aires
    0.27
    ials
    0.26
    orge
    0.25
    æ¡Ī
    0.25
    å´¤
    0.25
    ements
    0.25
    ment
    0.25
    keit
    0.24
    agrams
    0.24
    Activations Density 0.010%

    No Known Activations