© 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. 107943
    Prev
    Next
    INDEX
    Explanations

    Legal documents and web data

    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
    å¹´æĬ¥
    -0.29
     dul
    -0.28
    ictim
    -0.28
    ifton
    -0.27
    溢价
    -0.27
    idental
    -0.26
     incompet
    -0.25
    é²µ
    -0.25
    asher
    -0.25
    åĪļéľĢ
    -0.24
    POSITIVE LOGITS
    olars
    0.30
    æĮģä»ĵ
    0.28
    ump
    0.28
    èĩĤ
    0.27
    èµĮ
    0.26
    lm
    0.26
    è£ģåĪ¤
    0.26
    REAM
    0.26
    追
    0.25
    gu
    0.25
    Activations Density 0.909%

    No Known Activations