© 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. 33-TRANSCODER-HP
    7. 53934
    Prev
    Next
    INDEX
    Explanations

    love

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ycastle
    -0.27
    eci
    -0.26
    blocking
    -0.25
    elim
    -0.25
    æĭ¦æĪª
    -0.24
     Unblock
    -0.24
    æľŁåĨħ
    -0.24
    بار
    -0.24
    Elim
    -0.24
    VERR
    -0.23
    POSITIVE LOGITS
     job
    0.30
    å¦Ĥæŀľä¸įæĺ¯
    0.29
    对
    0.28
     of
    0.28
    å°į
    0.27
    _job
    0.26
    \/
    0.26
    éļ¶å±ŀäºİ
    0.26
    对åŃ©åŃIJ
    0.25
    çļĦ人éĥ½
    0.25
    Activations Density 0.006%

    No Known Activations