© 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. 23699
    Prev
    Next
    INDEX
    Explanations

    -push

    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
    éļĶ
    -0.28
     Muscle
    -0.24
    çŃĭ
    -0.24
    dü
    -0.24
    IDD
    -0.23
    resent
    -0.23
    ixon
    -0.23
    croft
    -0.23
    ä¸ĬéĻIJ
    -0.22
     åĪĨ
    -0.22
    POSITIVE LOGITS
    æīĢæıIJä¾Ľ
    0.30
    æīĢæıIJä¾ĽçļĦ
    0.27
    ghi
    0.26
    éģµå®Ī
    0.26
    å°ģ建
    0.24
    owing
    0.24
    malink
    0.24
    VED
    0.24
    æĪijçľĭ
    0.24
    inux
    0.24
    Activations Density 0.000%

    No Known Activations