© 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. 162225
    Prev
    Next
    INDEX
    Explanations

    we

    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
     panic
    -0.29
    ensively
    -0.28
    ä¾Ŀèµĸ
    -0.28
    RIX
    -0.26
    æ¡£
    -0.25
     Gala
    -0.25
    op
    -0.25
    éī´å®ļ
    -0.25
    åĬłæ²¹
    -0.24
    Op
    -0.24
    POSITIVE LOGITS
    ÑĩÑĮ
    0.28
    abay
    0.27
    autop
    0.26
    ä¸İæĹ¶ä¿±è¿Ľ
    0.25
    orth
    0.25
     """.
    0.25
     utmost
    0.25
    ksen
    0.25
    odont
    0.24
    hue
    0.24
    Activations Density 0.006%

    No Known Activations