© 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. 27-TRANSCODER-HP
    7. 57931
    Prev
    Next
    INDEX
    Explanations

    location change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >Action
    -0.29
    Top
    -0.28
    roller
    -0.27
    æĮĤåľ¨
    -0.26
     altogether
    -0.26
     interacting
    -0.26
     attached
    -0.26
    åĪĨå¸ĥåľ¨
    -0.25
    both
    -0.25
    éĢĴç»Ļ
    -0.24
    POSITIVE LOGITS
     spot
    0.29
    å°Ĭ
    0.28
     princ
    0.27
     impecc
    0.27
    ä»»
    0.27
    -spot
    0.27
    ä»»æķĻ
    0.26
    æĸ°ãģĹãģĦ
    0.26
     newfound
    0.26
     corro
    0.26
    Activations Density 0.002%

    No Known Activations