© 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. 20-TRANSCODER-HP
    7. 129378
    Prev
    Next
    INDEX
    Explanations

    phen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iani
    -0.28
     willingly
    -0.26
    orks
    -0.25
     voluntarily
    -0.25
    tings
    -0.24
     appropriation
    -0.24
    agh
    -0.23
    åİĿ
    -0.23
    iang
    -0.23
    amenti
    -0.23
    POSITIVE LOGITS
     star
    0.28
    çĥŃçĤ¹
    0.28
    ä¸ĢäºĮ
    0.28
    squ
    0.27
    å®ļçĤ¹
    0.26
    wap
    0.26
    acity
    0.25
    TemplateName
    0.25
    åŃĹ第
    0.24
    sil
    0.24
    Activations Density 1.456%

    No Known Activations