© 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. 41586
    Prev
    Next
    INDEX
    Explanations

    mentoring

    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
    íķij
    -0.31
    ients
    -0.29
     popping
    -0.27
     incident
    -0.27
     popped
    -0.27
     slap
    -0.26
     modal
    -0.26
    igh
    -0.26
     modules
    -0.25
     map
    -0.25
    POSITIVE LOGITS
    cade
    0.28
    ä¸ľè¥¿
    0.25
    Ze
    0.24
    岫
    0.24
    iter
    0.24
    cobra
    0.24
    çĽħ
    0.23
    èľľ
    0.23
    åĬ£
    0.23
    å¡ŀ
    0.23
    Activations Density 0.001%

    No Known Activations