© 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. 23-TRANSCODER-HP
    7. 24083
    Prev
    Next
    INDEX
    Explanations

    difficult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scenario
    -0.30
     scenario
    -0.28
     scenarios
    -0.28
    Scenario
    -0.27
    离åŃIJ
    -0.27
    -collapse
    -0.25
    (sc
    -0.24
    ä¸ĸçķĮè§Ĥ
    -0.24
     Concent
    -0.24
    ãģªãģĦãģĵãģ¨
    -0.24
    POSITIVE LOGITS
     difficulty
    0.37
    å¾Īéļ¾
    0.34
    usive
    0.34
     ease
    0.33
     dific
    0.33
     difficult
    0.32
     difficulties
    0.32
    Difficulty
    0.32
    åĽ°éļ¾
    0.32
    difficulty
    0.31
    Activations Density 0.017%

    No Known Activations