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. 130872
    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
     uniquely
    -0.07
    .emf
    -0.07
    loff
    -0.07
     Созд
    -0.07
     uv
    -0.07
    dux
    -0.07
    (obj
    -0.07
    кра
    -0.07
    шир
    -0.06
    (cfg
    -0.06
    POSITIVE LOGITS
    ][$
    0.07
    	RE
    0.07
    .languages
    0.07
    _elt
    0.07
    CATEGORY
    0.06
     WATER
    0.06
    important
    0.06
    _contents
    0.06
    ”
    0.06
    _FA
    0.06
    Activations Density 0.003%

    No Known Activations