© 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. 32-TRANSCODER-HP
    7. 41910
    Prev
    Next
    INDEX
    Explanations

    alongside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    秩
    -0.28
    Shape
    -0.26
    .observable
    -0.26
    è¡¿
    -0.24
     def
    -0.24
    abella
    -0.24
    大家éĥ½
    -0.24
    _shape
    -0.24
    å½¢
    -0.24
    è§Ĥ
    -0.24
    POSITIVE LOGITS
    æ°´æĻ¶
    0.26
    Cad
    0.25
     Satellite
    0.25
     Cad
    0.25
    éħ¬
    0.24
     Omni
    0.24
     cose
    0.24
     Pist
    0.24
    åį«æĺŁ
    0.24
    asel
    0.24
    Activations Density 0.047%

    No Known Activations