© 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. 30-TRANSCODER-HP
    7. 95880
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    溢
    -0.32
    å¸Ĥåİ¿
    -0.31
    ÄĻdzi
    -0.29
    ä¸Ģæīĭ
    -0.27
    local
    -0.26
    åIJĦåİ¿
    -0.26
    积
    -0.26
    翻身
    -0.26
    å®ļçĤ¹
    -0.25
    åĪĨæµģ
    -0.25
    POSITIVE LOGITS
    jos
    0.27
     Reserve
    0.26
    iste
    0.26
    enate
    0.26
    Shares
    0.25
     dziaÅĤ
    0.25
    ia
    0.24
    èĻİåį«
    0.24
    åIJįåĪĹ
    0.24
    RestController
    0.24
    Activations Density 0.118%

    No Known Activations