© 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. 149602
    Prev
    Next
    INDEX
    Explanations

    News/business announcements

    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
    åħ±
    -0.32
    usher
    -0.30
    éļħ
    -0.29
     hbox
    -0.27
     Assigned
    -0.25
    PFN
    -0.25
    fcc
    -0.25
    cej
    -0.25
    è§ĴèIJ½
    -0.25
    æłijæŀĿ
    -0.25
    POSITIVE LOGITS
    iming
    0.28
    olic
    0.27
    è¿Ļ个
    0.25
     this
    0.25
    çľ¼åħī
    0.25
    çħĻ
    0.25
    ç»Īäºİ
    0.24
    çĽ¼
    0.24
    å¿ħè¦ģçļĦ
    0.24
    Jacob
    0.24
    Activations Density 0.947%

    No Known Activations