Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-RESID-POST-AA
    6. 169
    Prev
    Next
    INDEX
    Explanations

    payments and salaries

    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
    rebbe
    -0.08
    =default
    -0.07
    -suite
    -0.07
    -review
    -0.07
    ≂
    -0.07
    pecies
    -0.07
    county
    -0.06
     waive
    -0.06
     cazzo
    -0.06
     Excellent
    -0.06
    POSITIVE LOGITS
     Dirt
    0.07
    গ
    0.07
     bugün
    0.07
    上汽
    0.06
     côt
    0.06
    ALTER
    0.06
    Ngu
    0.06
     ưu
    0.06
     Bölge
    0.06
    粪
    0.06
    Activations Density 0.054%

    No Known Activations