© 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. 853
    Prev
    Next
    INDEX
    Explanations

    sports clubs

    np_max-act-logits · gemini-2.0-flash
    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
    ถา
    -0.08
     vp
    -0.07
    루
    -0.07
    案子
    -0.07
     Venue
    -0.07
    箱子
    -0.06
     Rule
    -0.06
     المو
    -0.06
    洙
    -0.06
     Tình
    -0.06
    POSITIVE LOGITS
    getId
    0.07
    Ҁ
    0.07
     jail
    0.07
    odynamic
    0.07
    ической
    0.07
    とともに
    0.07
     remainder
    0.07
    是不可能
    0.06
     oat
    0.06
     SYS
    0.06
    Activations Density 0.007%

    No Known Activations