© 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. 163506
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ä¾Ŀæŧ
    -0.28
    溢
    -0.28
     chÃŃ
    -0.27
    sic
    -0.27
    è®°å¾Ĺ
    -0.26
    è§Ħ模æľĢ大
    -0.26
    æĺ¯ä¸įæĺ¯
    -0.26
     prev
    -0.25
     frozen
    -0.25
    (prev
    -0.24
    POSITIVE LOGITS
    legates
    0.30
    论述
    0.28
     explan
    0.27
    ä»ĭç´¹
    0.26
    ventions
    0.26
    å®ŀçĶ¨
    0.25
    -angular
    0.25
    auses
    0.25
    ä»ĭç»į
    0.25
    arness
    0.25
    Activations Density 0.001%

    No Known Activations