© 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. 22-TRANSCODER-HP
    7. 111796
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     treff
    -0.28
     should
    -0.27
    åºĶå½ĵ
    -0.27
     manus
    -0.26
    .sap
    -0.26
    çĪª
    -0.26
    quals
    -0.25
     shouldn
    -0.25
     kla
    -0.25
    should
    -0.25
    POSITIVE LOGITS
     deemed
    0.30
    被认为
    0.29
    .jetbrains
    0.29
    åıĹ
    0.28
    åij¼å£°
    0.28
    ESCO
    0.26
     Whole
    0.25
     Accepted
    0.24
    æıIJè®®
    0.24
    Accepted
    0.24
    Activations Density 0.001%

    No Known Activations