© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107136
    Prev
    Next
    INDEX
    Explanations

    Anime related

    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
    Negative Logits
    京
    -0.27
    æ²½
    -0.26
    igli
    -0.26
    详
    -0.25
    èĩªè¡Į车
    -0.25
    aat
    -0.25
    rift
    -0.25
    å®īåħ¨ä¿Ŀéļľ
    -0.24
    ymb
    -0.24
    TemplateName
    -0.24
    POSITIVE LOGITS
    饲
    0.30
    entai
    0.30
     Chapter
    0.28
    Reader
    0.28
     maid
    0.28
     anime
    0.28
    çĶ·ä¸»
    0.28
    éĻIJæľŁ
    0.27
     reader
    0.27
    -reader
    0.27
    Activations Density 1.658%

    No Known Activations