© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 40470
    Prev
    Next
    INDEX
    Explanations

    Company

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Further
    -0.08
     contrad
    -0.07
    무
    -0.07
     passwd
    -0.07
    _Q
    -0.07
     mai
    -0.07
     **
    -0.07
    _cpu
    -0.07
    □
    -0.06
    בסוף
    -0.06
    POSITIVE LOGITS
     Chile
    0.07
    玛丽
    0.07
     Scala
    0.07
     outcry
    0.07
    精灵
    0.06
    .Cancel
    0.06
     Thần
    0.06
    صل
    0.06
     QLabel
    0.06
    names
    0.06
    Activations Density 0.011%

    No Known Activations