© 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. 108518
    Prev
    Next
    INDEX
    Explanations

    heart and feelings

    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
    客
    -0.31
    ertime
    -0.25
    roat
    -0.25
    对æĪijæĿ¥è¯´
    -0.24
    æĺ¯æĪijçļĦ
    -0.24
    ouple
    -0.24
     intimidating
    -0.24
     substr
    -0.24
     Scha
    -0.24
     Suns
    -0.24
    POSITIVE LOGITS
     heart
    0.27
     hạt
    0.27
     pattern
    0.27
    å¿ĥ
    0.27
    scenario
    0.26
     scenario
    0.26
    å¿Ĺ
    0.26
    č↵    č↵
    0.26
     scenarios
    0.26
    Heart
    0.26
    Activations Density 0.937%

    No Known Activations