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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161916
    Prev
    Next
    INDEX
    Explanations

    potential

    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
    stand
    -0.29
    éĹ®é¢ĺ
    -0.26
    itches
    -0.26
    êµIJ
    -0.25
    çĦ¦èĻij
    -0.25
    åĽŀåIJĪ
    -0.25
    æ³Ľ
    -0.25
     Issues
    -0.24
    ä¹±
    -0.24
    çݰ象
    -0.24
    POSITIVE LOGITS
    æ½ľèĥ½
    0.30
    æīĢèĥ½
    0.29
    åĬŁæķĪ
    0.27
     ability
    0.27
    ablish
    0.26
    çļĦä¸Ģ款
    0.26
    tsy
    0.25
     rôle
    0.25
    çļĦä¸Ģ项
    0.25
     envision
    0.25
    Activations Density 0.012%

    No Known Activations