© 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. 25-TRANSCODER-HP
    7. 107408
    Prev
    Next
    INDEX
    Explanations

    swept

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŁ¹åħ»
    -0.28
    _BACK
    -0.28
    èĬĤ
    -0.26
    nty
    -0.26
    çĸĻ
    -0.25
    åħ»æĬ¤
    -0.24
    cour
    -0.24
    çĻ¾åĪĨ
    -0.24
     @(
    -0.24
    ounty
    -0.24
    POSITIVE LOGITS
    outs
    0.31
    ä¹ĭåĬ¿
    0.27
    èĩªæĿ¥
    0.27
    äºĨä»ĸçļĦ
    0.26
    äºĨä¸ĢäºĽ
    0.26
    äºĨä¸Ģæī¹
    0.26
    Ñħа
    0.25
    gram
    0.25
    ose
    0.24
    ì§Ħ
    0.24
    Activations Density 0.157%

    No Known Activations