© 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. 22-TRANSCODER-HP
    7. 88064
    Prev
    Next
    INDEX
    Explanations

    Appear/seem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igner
    -0.26
    åįģä¸ĩ
    -0.25
    å°¿
    -0.25
    ús
    -0.25
    äºĶåįĥ
    -0.24
     Exercise
    -0.23
     exercise
    -0.23
    _NOP
    -0.23
     '\''
    -0.23
    èĥį
    -0.23
    POSITIVE LOGITS
    dire
    0.28
    afil
    0.27
    ingly
    0.27
     rebound
    0.26
    reno
    0.26
    ’e
    0.25
     suggesting
    0.24
    æľīä»Ģä¹Ī
    0.24
    THR
    0.24
    å®ŀå®ŀåľ¨åľ¨
    0.24
    Activations Density 0.053%

    No Known Activations