© 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. 23-TRANSCODER-HP
    7. 24492
    Prev
    Next
    INDEX
    Explanations

    through

    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
    é£İæīĩ
    -0.31
    åħ¼å®¹
    -0.26
     compat
    -0.26
    çªĹæĪ·
    -0.26
    agra
    -0.24
    ä¸İåħ¶ä»ĸ
    -0.24
    éŸ
    -0.24
    compat
    -0.24
     ribbon
    -0.24
     expanded
    -0.23
    POSITIVE LOGITS
    æĿ¥çļĦ
    0.29
    æīĭ游
    0.27
    åī§ä¸Ń
    0.26
    樾
    0.25
    whel
    0.25
    ä»Ģä¹Īéĥ½
    0.25
    RequiredMixin
    0.24
     owed
    0.24
     Foot
    0.24
    tere
    0.24
    Activations Density 0.002%

    No Known Activations