© 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. 30-TRANSCODER-HP
    7. 96308
    Prev
    Next
    INDEX
    Explanations

    education and careers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĶ½
    -0.29
     Duis
    -0.26
     agrees
    -0.26
     ActiveForm
    -0.26
    ayan
    -0.26
    éĢļçķħ
    -0.25
    ượng
    -0.25
    fdc
    -0.24
    kins
    -0.24
    äºĶåįĥ
    -0.24
    POSITIVE LOGITS
    æĭ¥æľī
    0.43
    åħ·æľī
    0.43
    æĵģæľī
    0.41
     possession
    0.39
     holding
    0.38
     possessing
    0.37
     possess
    0.37
     earning
    0.35
    æĮģæľī
    0.35
     possesses
    0.35
    Activations Density 0.883%

    No Known Activations