© 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. 163781
    Prev
    Next
    INDEX
    Explanations

    Text extraction

    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
    æĶ¹éĢł
    -0.28
    åķĨä¼ļ
    -0.27
    esz
    -0.27
     sluts
    -0.26
     regenerated
    -0.26
     rib
    -0.26
    åĩĨåĪĻ
    -0.26
    ertino
    -0.24
    nock
    -0.24
    ä¸Ĭæ±½
    -0.24
    POSITIVE LOGITS
     Chain
    0.27
    زÙĨ
    0.25
    æĸŃ
    0.25
    éĵ
    0.25
    drive
    0.24
     Teach
    0.24
     Sup
    0.24
    _SCAN
    0.23
     Conn
    0.23
    ANCE
    0.23
    Activations Density 0.002%

    No Known Activations