© 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. 19-RESID-POST-AA
    11. 9079
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Petr
    -0.08
    保罗
    -0.08
     Ashe
    -0.08
     exploitation
    -0.07
    引力
    -0.07
    琶
    -0.07
    aktiv
    -0.07
     lamb
    -0.07
     Pell
    -0.07
    thal
    -0.06
    POSITIVE LOGITS
    constraints
    0.08
    (argv
    0.08
    	void
    0.07
     partnering
    0.07
    퓮
    0.07
    力争
    0.06
    )↵↵↵
    0.06
     basis
    0.06
     inconvenience
    0.06
    .Controllers
    0.06
    Activations Density 0.011%

    No Known Activations