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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163398
    Prev
    Next
    INDEX
    Explanations

    to

    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
    æīĵ交éģĵ
    -0.31
    ÑģÑħ
    -0.27
    æĶ¶çĽĬçİĩ
    -0.26
    欢è¿İ
    -0.25
    _commands
    -0.25
     overturn
    -0.25
    çĥŃ线
    -0.25
    onet
    -0.24
    ç½ijéĢļ
    -0.24
     spoon
    -0.24
    POSITIVE LOGITS
    esses
    0.26
     getContentPane
    0.25
     centers
    0.25
    .Apis
    0.25
     Eh
    0.24
    åıĪ被
    0.24
    ç¢
    0.24
     activity
    0.24
    	usage
    0.24
    .Qual
    0.24
    Activations Density 0.022%

    No Known Activations