© 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. 27-TRANSCODER-HP
    7. 57137
    Prev
    Next
    INDEX
    Explanations

    statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Dataset
    -0.27
    éĩĬæĶ¾
    -0.26
    inha
    -0.25
    ä»Ģä¹Īäºĭ
    -0.25
    æĿ¯
    -0.25
    æ¯ı次
    -0.24
    -align
    -0.24
    篮
    -0.24
    è¿Ŀ约
    -0.24
    .getCount
    -0.24
    POSITIVE LOGITS
    esco
    0.28
    ITT
    0.26
    çĽ¸ä¿¡å¤§å®¶
    0.26
    缸åħ³çļĦ
    0.25
    CVE
    0.25
    FOUNDATION
    0.25
    Ñģка
    0.25
     dispos
    0.25
     pep
    0.24
    }'",
    0.24
    Activations Density 0.007%

    No Known Activations