© 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. 53380
    Prev
    Next
    INDEX
    Explanations

    Ign

    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
     ignores
    -0.31
    æĢł
    -0.30
     ignored
    -0.30
    MeasureSpec
    -0.29
    aben
    -0.29
    忽çķ¥
    -0.28
    æĶ¾å¼ĥ
    -0.28
     ignoring
    -0.28
     ignore
    -0.28
     overlook
    -0.28
    POSITIVE LOGITS
    oc
    0.31
    rico
    0.29
    otti
    0.28
    æī©å¼ł
    0.27
    æī©
    0.27
    交
    0.26
     cal
    0.26
    æ¿Ģåħī
    0.26
    ACC
    0.26
     rico
    0.26
    Activations Density 0.005%

    No Known Activations