© 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. 9-TRANSCODER-HP
    7. 30081
    Prev
    Next
    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬĢæľ¯äººåijĺ
    -0.29
    éŃħåĬĽ
    -0.27
    æī¿è½½
    -0.26
    æī¹åĩĨ
    -0.25
     approving
    -0.25
    æĵ¦
    -0.25
     оÑĩеÑĢед
    -0.25
    inka
    -0.25
    å¾Īæ£Ĵ
    -0.24
    çī¹æ´¾
    -0.24
    POSITIVE LOGITS
    onds
    0.26
    aims
    0.26
    ãĥ¼ãĤ¹
    0.25
    indic
    0.25
    ario
    0.25
     bud
    0.24
    rott
    0.24
    eller
    0.24
    rips
    0.24
    reading
    0.24
    Activations Density 3.512%

    No Known Activations