© 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. 23388
    Prev
    Next
    INDEX
    Explanations

    code, markup

    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
    å®ĥçļĦ
    -0.30
    eea
    -0.27
    è¿Ļ座
    -0.26
     meis
    -0.26
    icut
    -0.26
    lers
    -0.26
    侥幸
    -0.26
     VIA
    -0.25
    txn
    -0.24
    ey
    -0.24
    POSITIVE LOGITS
    DrawerToggle
    0.27
     equ
    0.27
    çłģ
    0.26
    rı
    0.26
    éĹŃ
    0.25
    ä¸įå¤Ł
    0.25
    èģĶ
    0.25
    NotFound
    0.25
    çĸ¯
    0.25
    æĽ¿è¡¥
    0.24
    Activations Density 0.000%

    No Known Activations