© 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. 31-TRANSCODER-HP
    7. 18263
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _literals
    -0.27
     Adv
    -0.27
    çĶµè¯Ŀ
    -0.27
     GetAll
    -0.26
     neutrality
    -0.26
    å¼ķåıijäºĨ
    -0.26
    产çĶŁäºĨ
    -0.26
    éľİ
    -0.26
     getAll
    -0.26
    LETE
    -0.25
    POSITIVE LOGITS
     best
    0.31
    å®°
    0.30
    amin
    0.29
    æľĢä½³
    0.29
    åħ¥
    0.29
    éĥ½åı¯ä»¥
    0.28
    èħ±
    0.28
     can
    0.27
     lift
    0.27
    çŃĶæ¡Ī
    0.27
    Activations Density 0.003%

    No Known Activations