© 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. 150713
    Prev
    Next
    INDEX
    Explanations

    during

    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
    å¤Ł
    -0.27
    æľŁåĨħ
    -0.26
    trip
    -0.26
    ovie
    -0.26
    迹
    -0.25
    strate
    -0.25
    æĸ°ä¸ĸ纪
    -0.25
    ibo
    -0.24
    çļĦ身ä½ĵ
    -0.24
    Facing
    -0.24
    POSITIVE LOGITS
     telegram
    0.25
    çĶ±æѤ
    0.25
     Herm
    0.25
     Miner
    0.25
     smarty
    0.24
     Grü
    0.24
     darken
    0.24
     pd
    0.24
     shout
    0.24
     Balt
    0.24
    Activations Density 0.122%

    No Known Activations