Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88190
    Prev
    Next
    INDEX
    Explanations

    ed

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afi
    -0.08
     Ago
    -0.08
    "g
    -0.07
    觥
    -0.07
    他已经
    -0.07
    })",
    -0.07
    üğü
    -0.07
    "]}
    -0.07
     esl
    -0.06
     jim
    -0.06
    POSITIVE LOGITS
    홀
    0.07
     Stark
    0.07
    рад
    0.07
     inherits
    0.07
    قضاء
    0.06
    archy
    0.06
    RL
    0.06
    ainted
    0.06
    Random
    0.06
    elerik
    0.06
    Activations Density 0.001%

    No Known Activations