© 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. 25-TRANSCODER-HP
    7. 107792
    Prev
    Next
    INDEX
    Explanations

    mental health, code, struggles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     told
    -0.29
     remainder
    -0.27
    çłĶ究éĻ¢
    -0.26
    èµ¢å¾ĹäºĨ
    -0.26
    .defaults
    -0.26
    annes
    -0.25
    nuts
    -0.25
     Font
    -0.25
    åīįä»»
    -0.24
    ends
    -0.24
    POSITIVE LOGITS
    mesh
    0.28
    isman
    0.28
    è¿ĩå¤ļ
    0.27
    WidgetItem
    0.27
    æĦŁåĪ°
    0.26
    ORED
    0.26
    ä¸ĩ人次
    0.26
    олог
    0.25
    whel
    0.25
    urement
    0.25
    Activations Density 0.925%

    No Known Activations