© 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. 22336
    Prev
    Next
    INDEX
    Explanations

    G

    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
    罩
    -0.28
    çļĦè¿ĽæŃ¥
    -0.26
    æłª
    -0.26
    è¿ĻäºĽä¸ľè¥¿
    -0.26
    (alias
    -0.25
    ices
    -0.25
    atron
    -0.25
     OTHERWISE
    -0.24
    æµİ
    -0.24
    å¯IJ
    -0.24
    POSITIVE LOGITS
    endir
    0.30
    å®ļçĤ¹
    0.28
    YPE
    0.25
    velte
    0.25
     whisk
    0.24
    —but
    0.24
    ç²Ĺ
    0.24
    uzzer
    0.24
    plr
    0.24
    -white
    0.24
    Activations Density 0.098%

    No Known Activations