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. 72568
    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
    環境
    -0.07
    şık
    -0.07
    맑
    -0.07
     bag
    -0.07
    택
    -0.07
    yeah
    -0.06
     immune
    -0.06
    ază
    -0.06
    موظف
    -0.06
    Issue
    -0.06
    POSITIVE LOGITS
    Break
    0.08
     RP
    0.07
     وقد
    0.07
     nomination
    0.07
     riv
    0.07
     Scor
    0.07
     cel
    0.07
     SELF
    0.07
    一次
    0.07
    (CG
    0.07
    Activations Density 0.006%

    No Known Activations