© 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. 15-RESID-POST-AA
    11. 129325
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparent
    -0.07
    stdClass
    -0.07
    чем
    -0.07
    公认
    -0.07
    在我国
    -0.07
     dripping
    -0.07
    决策部署
    -0.07
    第三者
    -0.07
     shutting
    -0.06
    сто
    -0.06
    POSITIVE LOGITS
     times
    0.07
    弑
    0.07
    𝚖
    0.06
    elim
    0.06
    涂抹
    0.06
    assandra
    0.06
    槃
    0.06
    lparr
    0.06
    bara
    0.06
    dzić
    0.06
    Activations Density 0.234%

    No Known Activations