© 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. 163469
    Prev
    Next
    INDEX
    Explanations

    0

    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
    æĺ¨
    -0.29
    æģķ
    -0.28
    ç¥ĵ
    -0.27
    ç½ij讯
    -0.27
     offsetof
    -0.26
    alsy
    -0.25
    ipple
    -0.25
    otics
    -0.25
    éļħ
    -0.25
    ogl
    -0.24
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.29
    éĻħ
    0.26
    2
    0.26
    è§Ĩ
    0.25
    ä¸ĭè¾¾
    0.25
    ä¾Ŀçħ§
    0.24
     Bills
    0.24
    ย
    0.24
    举æݪ
    0.24
    Y
    0.24
    Activations Density 0.003%

    No Known Activations