© 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. 12-TRANSCODER-HP
    7. 23801
    Prev
    Next
    INDEX
    Explanations

    NC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GRE
    -0.27
    çľģ
    -0.27
    åij½
    -0.26
     lip
    -0.25
    çľģå§Ķ
    -0.25
     hun
    -0.24
    ç²®
    -0.24
    æ´»çĿĢ
    -0.24
    mob
    -0.24
     skipped
    -0.24
    POSITIVE LOGITS
    ainer
    0.26
    èµIJ
    0.25
    å®Įå·¥
    0.25
    udas
    0.24
    ä½ij
    0.23
    æű
    0.23
    ãĥķãĤ©ãĥ¼
    0.23
    fty
    0.23
     amassed
    0.23
    èĢģåŃĹåı·
    0.23
    Activations Density 0.080%

    No Known Activations