© 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. 162518
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     loft
    -0.26
     retiring
    -0.26
    æĪĺ士æĿ¥è¯´
    -0.26
    LAB
    -0.25
    ê±°ëĤĺ
    -0.25
    aten
    -0.25
     rumors
    -0.24
    çĮľæµĭ
    -0.24
    nect
    -0.24
    说æĺ¯
    -0.24
    POSITIVE LOGITS
    注æĦı
    0.26
     normally
    0.25
    .dat
    0.24
     attendant
    0.24
    请çĤ¹åĩ»
    0.23
     allied
    0.23
    æ³°
    0.23
    åģļæ³ķ
    0.23
    æīĭæ³ķ
    0.23
     manual
    0.23
    Activations Density 0.010%

    No Known Activations