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. 131012
    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
    法师
    -0.08
    tility
    -0.07
    ൽ
    -0.07
     artistic
    -0.07
     afflict
    -0.07
     mensen
    -0.07
     Romantic
    -0.07
    opic
    -0.07
    出境
    -0.07
     verm
    -0.06
    POSITIVE LOGITS
     count
    0.07
     Canada
    0.07
    	gr
    0.07
    cba
    0.07
    :"
    0.06
    .LoadScene
    0.06
    everything
    0.06
     aligned
    0.06
    significant
    0.06
     Published
    0.06
    Activations Density 0.005%

    No Known Activations