© 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. 25208
    Prev
    Next
    INDEX
    Explanations

    Fulfilling requirements and demands

    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
    uppet
    -0.25
    代è¨Ģ人
    -0.25
    EqualTo
    -0.24
    æ´¾
    -0.24
    -approved
    -0.24
    ustering
    -0.24
    ONENT
    -0.24
    Rad
    -0.23
    EEP
    -0.23
    Bindable
    -0.23
    POSITIVE LOGITS
    çļĦä¸įåIJĮ
    0.34
    éľĢæ±Ĥ
    0.33
    çļĦéľĢæ±Ĥ
    0.33
     needs
    0.31
    åıĺåĮĸ
    0.30
     changing
    0.30
    æĹ¥çĽĬ
    0.29
     Vaults
    0.29
    çļĦåıĺåĮĸ
    0.29
     varying
    0.29
    Activations Density 0.005%

    No Known Activations