© 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. 53273
    Prev
    Next
    INDEX
    Explanations

    SN

    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
     bul
    -0.28
    bul
    -0.28
    edb
    -0.27
    å¹¢
    -0.27
    eel
    -0.26
    éĺµ
    -0.25
    eon
    -0.25
    oe
    -0.25
    oi
    -0.25
     Probe
    -0.25
    POSITIVE LOGITS
    osopher
    0.28
    mons
    0.27
    aret
    0.27
    Mer
    0.27
     Mer
    0.26
    好人
    0.26
    male
    0.26
    MER
    0.25
     Accepted
    0.25
    mer
    0.25
    Activations Density 0.008%

    No Known Activations