© 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. 42391
    Prev
    Next
    INDEX
    Explanations

    respect

    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
     Bite
    -0.30
    opian
    -0.26
    ¹Ħ
    -0.25
     bite
    -0.25
    åĬĽæ±Ĥ
    -0.25
     Including
    -0.24
    jos
    -0.24
    estone
    -0.24
    iture
    -0.23
    phans
    -0.23
    POSITIVE LOGITS
     respect
    1.82
     Respect
    1.43
     respects
    1.42
    å°Ĭéĩį
    1.41
    respect
    1.41
     respected
    1.31
    å°Ĭ
    1.22
     respecting
    1.21
     respectful
    1.05
    å°Ĭæķ¬
    1.02
    Activations Density 0.003%

    No Known Activations