© 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. 25-TRANSCODER-HP
    7. 108404
    Prev
    Next
    INDEX
    Explanations

    Pollution and waste removal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bles
    -0.27
    梯éĺŁ
    -0.27
    heim
    -0.26
    交éĢļ大åѦ
    -0.26
    åħĭæľį
    -0.26
     curls
    -0.25
    è¾ĵéĢģ
    -0.25
    æĬ¤èº«ç¬¦
    -0.24
    çĭ¬ç«ĭèij£äºĭ
    -0.24
    æĴµ
    -0.24
    POSITIVE LOGITS
    cht
    0.26
    pte
    0.26
    ä¸ĩ个
    0.25
    iones
    0.25
    iona
    0.25
    à¹ģมà¸Ļ
    0.25
    pls
    0.23
    缺å°ij
    0.23
    andid
    0.22
    ÙĬرة
    0.22
    Activations Density 0.920%

    No Known Activations