© 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. 95386
    Prev
    Next
    INDEX
    Explanations

    Chap

    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
    andum
    -0.28
    åĪĨæł¡
    -0.27
    ÑĢова
    -0.26
    /native
    -0.25
    çľ¼åīįçļĦ
    -0.25
    æĦıè¯Ĩå½¢æĢģ
    -0.24
    å°ģ
    -0.24
    æīĵæŃ»
    -0.24
    ucken
    -0.24
    rotein
    -0.24
    POSITIVE LOGITS
    è¶ħ
    0.25
    ãĥĥãĤ¯ãĤ¹
    0.25
    æİł
    0.25
     accept
    0.24
    çı
    0.24
     researcher
    0.24
    Floating
    0.24
     Kle
    0.24
    olumn
    0.24
    è´¿èµĤ
    0.24
    Activations Density 0.000%

    No Known Activations