© 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. 150616
    Prev
    Next
    INDEX
    Explanations

    Irregular vocabulary

    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
    èİ«è¿ĩäºİ
    -0.30
    enkins
    -0.27
    æ¯ħçĦ¶
    -0.27
    代表æĢ§
    -0.26
     convince
    -0.26
    enment
    -0.26
     willingly
    -0.26
     convincing
    -0.25
     convinced
    -0.25
     voluntarily
    -0.25
    POSITIVE LOGITS
    æĸ°çļĦä¸Ģ
    0.26
    æľķ
    0.25
    arily
    0.25
    æĸ°
    0.24
    ixel
    0.24
     Mu
    0.24
    çĤ¹å¤ļ
    0.24
    ew
    0.24
    IRD
    0.24
    #undef
    0.24
    Activations Density 0.940%

    No Known Activations