© 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. 24-TRANSCODER-HP
    7. 150003
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĽĭçĻ½
    -0.29
    protein
    -0.29
    obile
    -0.27
    éĦľ
    -0.25
    á
    -0.25
    å±ħ室
    -0.25
    èĽĭçĻ½è´¨
    -0.25
    asters
    -0.24
    轶
    -0.24
    ä¸ĵè¾ij
    -0.24
    POSITIVE LOGITS
    æ³¥
    0.26
     Rhodes
    0.26
     LATIN
    0.25
    cott
    0.25
     GMT
    0.25
    arness
    0.24
    æĶ¸
    0.23
     mourning
    0.23
     exited
    0.23
    åĽ½å®¶éĩįçĤ¹
    0.23
    Activations Density 0.900%

    No Known Activations