© 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. 41344
    Prev
    Next
    INDEX
    Explanations

    vert, inverse

    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
    as
    -0.28
    åĽĬ
    -0.27
    msp
    -0.26
     pitch
    -0.25
    ag
    -0.25
    è¤Ĵ
    -0.24
     rendering
    -0.24
    ÅĽÄĩ
    -0.24
     pitching
    -0.24
    pitch
    -0.24
    POSITIVE LOGITS
    verted
    0.37
    vert
    0.36
    inverse
    0.35
     inverse
    0.35
     inversion
    0.35
    verts
    0.34
    Inverse
    0.34
    éĢĨ转
    0.33
    åĢĴ
    0.33
     invert
    0.32
    Activations Density 0.000%

    No Known Activations