© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 129342
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Psychic
    -0.07
     język
    -0.07
    考察
    -0.07
    Ǐ
    -0.07
     sistemas
    -0.07
    庳
    -0.07
    UAL
    -0.06
     worship
    -0.06
    -Language
    -0.06
    Shopping
    -0.06
    POSITIVE LOGITS
     entr
    0.08
    _category
    0.07
    బ
    0.06
     heure
    0.06
     else
    0.06
    .opens
    0.06
    /categories
    0.06
    腘
    0.06
     أحد
    0.06
     zwe
    0.06
    Activations Density 0.122%

    No Known Activations