© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161969
    Prev
    Next
    INDEX
    Explanations

    Code, legal documents, technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾ģæĶ¶
    -0.28
    æĺ¯ä¸Ģç§į
    -0.27
    ','');↵
    -0.27
    ingham
    -0.26
     flux
    -0.25
    emplo
    -0.25
    å¾µ
    -0.25
    æĺ¯ä¸ª
    -0.25
    '],'
    -0.24
    ç°¸
    -0.24
    POSITIVE LOGITS
    Relations
    0.28
    åĨįåİ»
    0.28
     curs
    0.26
    dition
    0.25
    relations
    0.25
    æĸ°éĹ»è®°èĢħ
    0.24
    å¤ļä¹ħ
    0.24
    åĿIJä¸ĭ
    0.24
    缴è§Ĥ
    0.24
    pec
    0.23
    Activations Density 0.007%

    No Known Activations