© 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
    2. Qwen3-4B
    3. 31-TRANSCODER-HP
    4. 18543
    Prev
    Next
    INDEX
    Explanations

    ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¸ļ
    -0.28
    amic
    -0.27
    ç½ijé¦ĸ页
    -0.27
    ze
    -0.27
    hrs
    -0.25
    firm
    -0.24
    ÑĮÑı
    -0.24
    ages
    -0.24
    roids
    -0.24
    ilian
    -0.24
    POSITIVE LOGITS
    客åķĨ
    0.28
    踪
    0.26
    èĮ¶
    0.26
    æĴij
    0.25
    çĥ¦
    0.25
     Leh
    0.24
    èĦIJ
    0.24
    ä¸Ńè¶ħ
    0.24
    大èĩ£
    0.24
    cro
    0.23
    Activations Density 0.025%

    No Known Activations