© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 822
    Prev
    Next
    INDEX
    Explanations

    Database code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Markdown
    -0.07
     Desired
    -0.07
     mv
    -0.07
    terminal
    -0.07
     وجه
    -0.07
    石家庄
    -0.06
     البنك
    -0.06
    金沙
    -0.06
    ตาย
    -0.06
    ldap
    -0.06
    POSITIVE LOGITS
    视力
    0.07
    Weight
    0.07
    考评
    0.06
    油烟
    0.06
    疠
    0.06
    CallableWrapper
    0.06
     Eins
    0.06
     Coding
    0.06
    _p
    0.06
     Cor
    0.06
    Activations Density 0.013%

    No Known Activations