© 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. 162558
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
     attendance
    -0.27
     items
    -0.27
    åĺ¹
    -0.27
     pew
    -0.25
     tended
    -0.25
    @stop
    -0.25
    æĿ¥èĩª
    -0.25
     attend
    -0.24
    allon
    -0.24
    å½³
    -0.24
    POSITIVE LOGITS
    å½Ĵ
    0.30
     BASIS
    0.25
    ldr
    0.25
    å½±
    0.25
    çļĦæĪ¿åŃIJ
    0.24
    licos
    0.24
    æѸ
    0.24
     заÑĤ
    0.24
    ipers
    0.24
    reur
    0.24
    Activations Density 0.001%

    No Known Activations