© 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. 95816
    Prev
    Next
    INDEX
    Explanations

    Schizophrenia descriptions

    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
     sought
    -0.30
     Seeking
    -0.29
     seek
    -0.28
     textStyle
    -0.28
    Seek
    -0.27
     seeks
    -0.27
    AEA
    -0.26
    çĻ¾å¹´
    -0.26
    ä¹±
    -0.26
     yyn
    -0.26
    POSITIVE LOGITS
     core
    0.30
    flatten
    0.28
    core
    0.28
    æ¿Ģ
    0.28
    åĪ»
    0.28
    anh
    0.27
    .removeChild
    0.26
    æł¸å¿ĥ
    0.26
    _core
    0.26
    Core
    0.26
    Activations Density 0.987%

    No Known Activations