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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6829
    Prev
    Next
    INDEX
    Explanations

    Tkinter 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_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
    牙
    -0.07
     enlarged
    -0.07
    𝜏
    -0.06
    ussions
    -0.06
    骱
    -0.06
     у
    -0.06
     Marr
    -0.06
     fırsat
    -0.06
    伙伴关系
    -0.06
    ↜
    -0.06
    POSITIVE LOGITS
    _pcm
    0.08
    茓
    0.07
    acers
    0.07
    adds
    0.07
    	i
    0.07
     letras
    0.07
     currentTime
    0.06
     geli
    0.06
     card
    0.06
     Anth
    0.06
    Activations Density 0.063%

    No Known Activations