© 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. 338
    Prev
    Next
    INDEX
    Explanations

    ate

    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
    ä¸Ģ款
    -0.27
    å¿Ĵ
    -0.26
    è£ģ
    -0.25
    çĽijè§Ĩ
    -0.25
    ch
    -0.24
     tù
    -0.24
    Ctr
    -0.24
    Promise
    -0.24
    Lit
    -0.24
    æĸ°çĶŁ
    -0.23
    POSITIVE LOGITS
     luc
    0.28
    人人éĥ½
    0.27
    ;;;;;;;;;;;;;;;;
    0.27
    å¹³åĿĩæ¯ı
    0.26
    -des
    0.26
    lexer
    0.26
     devised
    0.25
    ogg
    0.25
     elect
    0.25
     sustaining
    0.25
    Activations Density 0.021%

    No Known Activations