© 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. 54227
    Prev
    Next
    INDEX
    Explanations

    allowing; permitting

    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
    LY
    -0.29
    leave
    -0.29
     Gross
    -0.28
    ely
    -0.27
    uale
    -0.26
    çķĻ
    -0.26
    outs
    -0.26
    mul
    -0.26
    æĬķå½±
    -0.24
     heads
    -0.24
    POSITIVE LOGITS
     let
    0.34
    让çĶ¨æĪ·
    0.31
    let
    0.28
     honor
    0.27
    åĭĸ
    0.27
     apologize
    0.26
     honour
    0.26
    	let
    0.26
    è¿Ľé©»
    0.26
     lets
    0.26
    Activations Density 0.030%

    No Known Activations