© 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. 7-RESID-POST-AA
    6. 39998
    Prev
    Next
    INDEX
    Explanations

    en

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    唱
    -0.07
     lyrics
    -0.07
     Being
    -0.07
    _pins
    -0.06
    Words
    -0.06
     thro
    -0.06
    纪念馆
    -0.06
    持續
    -0.06
    .Networking
    -0.06
    ERS
    -0.06
    POSITIVE LOGITS
    殡
    0.07
    thrown
    0.07
     Bubble
    0.07
    рук
    0.07
    порт
    0.07
     northeastern
    0.07
     parm
    0.07
     skipping
    0.07
     twenty
    0.07
    etermination
    0.06
    Activations Density 0.017%

    No Known Activations