© 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. 162584
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    紧紧
    -0.31
    åĪĩ
    -0.28
    æĬ±ä½ı
    -0.26
    ych
    -0.25
    ersh
    -0.24
    IGHT
    -0.24
    wife
    -0.24
    夫
    -0.23
     Wife
    -0.23
    lems
    -0.23
    POSITIVE LOGITS
    iscard
    0.31
    Breadcrumb
    0.26
    亡
    0.25
     plein
    0.25
    ellite
    0.24
    讫
    0.23
     ConfigureServices
    0.23
    æŶéĹ´æ®µ
    0.23
     inicio
    0.23
    letion
    0.23
    Activations Density 0.010%

    No Known Activations