© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    å®ĥ
    -0.34
    å®ĥæĺ¯
    -0.33
     them
    -0.30
     it
    -0.29
     nó
    -0.28
    ä»ĸ说
    -0.27
    caffe
    -0.27
    anas
    -0.27
    è´¯
    -0.27
    .cgi
    -0.26
    POSITIVE LOGITS
    çŃīåĨħ容
    0.26
    ä¸Ģ大æī¹
    0.26
    ä¸Ģç±»
    0.26
    çłĶ究æĪIJæŀľ
    0.26
     Newton
    0.25
    ä¸Ģæī¹
    0.25
    åѦçĶŁçļĦ
    0.24
    åŁºæľ¬åİŁåĪĻ
    0.24
    undred
    0.24
    ãģªãģ©ãģ®
    0.23
    Activations Density 0.025%

    No Known Activations