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. 131025
    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
    	pid
    -0.07
     Reid
    -0.07
    短板
    -0.07
    เสนอ
    -0.07
    дон
    -0.07
     Liberal
    -0.06
     Chính
    -0.06
     Mississippi
    -0.06
     Suggestions
    -0.06
     School
    -0.06
    POSITIVE LOGITS
     pathways
    0.08
    indic
    0.07
    ück
    0.07
    行星
    0.07
     Programs
    0.07
    			↵			↵
    0.07
     heavy
    0.07
    meth
    0.07
    .mods
    0.07
    마
    0.07
    Activations Density 0.070%

    No Known Activations