© 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. 22-TRANSCODER-HP
    7. 87167
    Prev
    Next
    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manageable
    -0.35
     okay
    -0.29
     acceptable
    -0.28
     Armed
    -0.28
    Fortunately
    -0.27
     harmless
    -0.27
     fortunately
    -0.27
     righteous
    -0.27
     Fortunately
    -0.27
    顺çķħ
    -0.27
    POSITIVE LOGITS
    åį´è¢«
    0.41
    çĦ¶èĢĮ
    0.38
     however
    0.37
    缺çĤ¹
    0.37
    ä½Ĩæĺ¯åľ¨
    0.35
    ä¸įæĸ¹ä¾¿
    0.35
    ä½Ĩæĺ¯
    0.35
    however
    0.35
    ä¹ŁéľĢè¦ģ
    0.35
    ä½Ĩæĺ¯æĪij
    0.35
    Activations Density 0.003%

    No Known Activations