© 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. 23299
    Prev
    Next
    INDEX
    Explanations

    software and coding

    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
    æĴ°
    -0.29
    âĦ
    -0.29
    ographically
    -0.26
    tier
    -0.26
     bbc
    -0.24
    ÑĤелÑĮно
    -0.24
    ily
    -0.24
     Ars
    -0.24
    ä¸įå®ľ
    -0.24
    (GLFW
    -0.24
    POSITIVE LOGITS
    çĶ°
    0.29
    为é¦ĸ
    0.29
    æ¶Īè´¹éľĢæ±Ĥ
    0.28
     cloning
    0.27
     sacr
    0.27
    åĩ¡
    0.27
    ãĥĬãĤ¤
    0.26
     kil
    0.26
    akra
    0.25
    usal
    0.25
    Activations Density 0.000%

    No Known Activations