© 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. 162566
    Prev
    Next
    INDEX
    Explanations

    perspectives

    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
    æĦŁ
    -0.25
    lâ
    -0.25
    obao
    -0.25
    äºĭå®ŀ
    -0.24
    ocz
    -0.24
    apy
    -0.24
    说å¾Ĺ
    -0.24
    å®ŀæĥł
    -0.24
    éĩįç»Ħ
    -0.24
    èĩªæ²»
    -0.23
    POSITIVE LOGITS
    大大å°ıå°ı
    0.32
    éķ¿çŁŃ
    0.30
     Ko
    0.28
    owns
    0.28
    bon
    0.28
    ermen
    0.27
    RODUCTION
    0.26
     ÐĿи
    0.26
     except
    0.25
    cess
    0.25
    Activations Density 0.008%

    No Known Activations