© 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. 108487
    Prev
    Next
    INDEX
    Explanations

    have

    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
    ılı
    -0.28
    oration
    -0.25
    帰ãĤĬ
    -0.25
    ä¸ĵ线
    -0.24
    million
    -0.24
    parison
    -0.24
    antine
    -0.24
    缸åĬ©
    -0.24
     willing
    -0.24
    çľī头
    -0.24
    POSITIVE LOGITS
     this
    0.35
    è¿Ļ个
    0.31
    è¿Ļä¸Ģ
    0.30
    ä¸Ģ个
    0.30
    this
    0.29
     THIS
    0.28
    è¿Ļæĺ¯ä¸Ģ个
    0.27
    è¿Ļç§į
    0.26
    pend
    0.26
    æľīä¸Ģ个
    0.25
    Activations Density 1.044%

    No Known Activations