© 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. 53881
    Prev
    Next
    INDEX
    Explanations

    European

    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
    .addHandler
    -0.28
    -exc
    -0.27
     rais
    -0.27
    åĢĴåľ¨
    -0.26
     Bring
    -0.25
    å½Ĵ
    -0.25
    ritte
    -0.24
    æĬĦ
    -0.24
    顺åºı
    -0.24
    åī¯æľ¬
    -0.24
    POSITIVE LOGITS
    ylan
    0.39
     Un
    0.36
    Un
    0.33
    -Un
    0.31
    anova
    0.30
    FACE
    0.28
    Ta
    0.27
     Union
    0.27
    .Un
    0.27
     UN
    0.27
    Activations Density 0.008%

    No Known Activations