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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129880
    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
     lsp
    -0.08
     esp
    -0.07
     perpetrators
    -0.07
    ict
    -0.06
    .Restrict
    -0.06
    tant
    -0.06
    運用
    -0.06
    完全
    -0.06
    薮
    -0.06
    𝓅
    -0.06
    POSITIVE LOGITS
     변수
    0.08
    Desde
    0.07
    istrar
    0.07
    uchar
    0.07
     voir
    0.07
     She
    0.07
     coincide
    0.07
    charts
    0.07
     Gear
    0.07
     stehen
    0.07
    Activations Density 0.014%

    No Known Activations