© 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. 42573
    Prev
    Next
    INDEX
    Explanations

    Spatial arrangements

    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
     happier
    -0.29
    éļ¾
    -0.29
     deceive
    -0.28
    å¤ĸåĽ½
    -0.28
     desper
    -0.28
    Haunted
    -0.26
    è¿Ľåı£
    -0.26
     fools
    -0.26
    æĺ§
    -0.26
    happy
    -0.25
    POSITIVE LOGITS
     vertical
    0.48
     perpendicular
    0.45
     linear
    0.45
     lateral
    0.44
     horizontal
    0.43
    åŀĤ缴
    0.41
     proportions
    0.40
     boundary
    0.40
    çĽ´çº¿
    0.39
    vertical
    0.38
    Activations Density 0.000%

    No Known Activations