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. 130790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     mes
    -0.08
     TY
    -0.07
     chap
    -0.06
     }]
    -0.06
     الكتاب
    -0.06
    _kel
    -0.06
    win
    -0.06
    ">↵
    -0.06
    親
    -0.06
     Consumers
    -0.06
    POSITIVE LOGITS
    _Internal
    0.08
    ivent
    0.07
     resizing
    0.07
     Greatest
    0.07
     shortest
    0.07
     reproductive
    0.07
    מגו
    0.07
    shortcut
    0.07
    っ�
    0.06
    .Dot
    0.06
    Activations Density 0.005%

    No Known Activations