© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107554
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿®æŃ£
    -0.29
    æĽ´å¤ļ
    -0.28
    orsi
    -0.27
     yyn
    -0.26
     correction
    -0.26
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.26
    åĪ®
    -0.26
    alsy
    -0.25
    åİĺ
    -0.25
    æĽ´å¤ļçļĦæĺ¯
    -0.25
    POSITIVE LOGITS
    ',)↵
    0.27
     palp
    0.27
     frm
    0.25
    没æľīä»Ģä¹Ī
    0.25
    ä¸įæŃ»
    0.24
    沸
    0.24
     single
    0.24
     Waves
    0.24
    äºĽ
    0.24
    åĪį
    0.23
    Activations Density 1.107%

    No Known Activations