© 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. 30-TRANSCODER-HP
    7. 96388
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meld
    -0.26
    æį
    -0.25
    MATRIX
    -0.25
     correct
    -0.24
    ç¾İèģĶ
    -0.24
    éĹ»
    -0.24
    ê¶Į
    -0.24
    ewolf
    -0.24
    åħ°èĬ±
    -0.24
    ä¸Ģä½ĵ
    -0.23
    POSITIVE LOGITS
    亲
    0.30
    retch
    0.29
    orial
    0.28
     transformation
    0.28
    éĩįæķ´
    0.26
    ecom
    0.26
    >Note
    0.26
     Spotlight
    0.25
    åŁ¹åħ»
    0.25
     rot
    0.25
    Activations Density 0.900%

    No Known Activations

    This feature has no known activations.