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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 580
    Prev
    Next
    INDEX
    Explanations

    Computer/app performance issues

    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
    Configuration
    -0.08
    -0.07
     vo
    -0.07
    Male
    -0.07
     xi
    -0.07
    问道
    -0.07
    -print
    -0.07
    סופר
    -0.06
    几位
    -0.06
     Toast
    -0.06
    POSITIVE LOGITS
     üzerinde
    0.08
    ϲ
    0.07
    sig
    0.07
     provid
    0.07
    砄
    0.07
    珋
    0.07
    itest
    0.07
    .Enums
    0.07
    SOEVER
    0.07
    etrain
    0.07
    Activations Density 0.122%

    No Known Activations