© 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. 702
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    _players
    -0.08
     الأخرى
    -0.07
     getType
    -0.07
    azor
    -0.07
    increments
    -0.07
    (Filter
    -0.07
     Rutgers
    -0.07
    priority
    -0.07
    ounters
    -0.07
    知名品牌
    -0.07
    POSITIVE LOGITS
    𝒊
    0.07
    𑘁
    0.06
    ุม
    0.06
     silence
    0.06
    ROME
    0.06
    ธ
    0.06
    ｽ
    0.06
     Cri
    0.06
     �
    0.06
    資訊
    0.06
    Activations Density 0.001%

    No Known Activations