© 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. 33-TRANSCODER-HP
    7. 53464
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    踩
    -0.28
    ayah
    -0.27
    è¡¥åĬ©
    -0.27
    åįıåĬŀ
    -0.26
     anch
    -0.25
     avail
    -0.24
    oman
    -0.24
    chet
    -0.24
    anje
    -0.23
    é©»
    -0.23
    POSITIVE LOGITS
     places
    0.50
     concepts
    0.41
     things
    0.40
    Places
    0.39
    places
    0.38
     scenarios
    0.35
    _places
    0.35
     relationships
    0.35
     conditions
    0.34
     Places
    0.34
    Activations Density 0.008%

    No Known Activations