© 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. 43126
    Prev
    Next
    INDEX
    Explanations

    technical/software context

    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
     Baz
    -0.27
    糧
    -0.24
     intervening
    -0.23
    éľľ
    -0.23
    aria
    -0.23
    -gnu
    -0.23
     Pee
    -0.23
    hardt
    -0.23
    ervation
    -0.23
    "context
    -0.22
    POSITIVE LOGITS
     effect
    1.43
    æķĪåºĶ
    1.24
    Effect
    1.16
     Effect
    1.13
    effect
    1.09
     effects
    1.05
     Effects
    1.01
    æķĪæŀľ
    0.98
    effects
    0.95
    -effect
    0.94
    Activations Density 0.002%

    No Known Activations