© 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. 24-TRANSCODER-HP
    7. 150721
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     randint
    -0.29
     blossom
    -0.28
    ķĮ
    -0.26
    æĶ¾å¼ĥäºĨ
    -0.25
    ettel
    -0.25
    rolley
    -0.25
    éĻIJãĤĬ
    -0.24
    RestController
    -0.24
     MutableList
    -0.24
    depends
    -0.24
    POSITIVE LOGITS
    nge
    0.27
    æĶ¾å¤§
    0.26
    æ¸ħæ´ģ
    0.26
     uncommon
    0.26
     goal
    0.25
    ipe
    0.24
    TRL
    0.24
     оÑĤзÑĭв
    0.24
     Vulner
    0.24
    个人
    0.24
    Activations Density 0.202%

    No Known Activations