© 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
    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. 682
    Prev
    Next
    INDEX
    Explanations

    Korean and code

    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
     страх
    -0.07
    oration
    -0.07
    פארק
    -0.07
     Cosmetic
    -0.07
     pracowników
    -0.06
    Leon
    -0.06
    akespeare
    -0.06
    quel
    -0.06
    奶油
    -0.06
    쬔
    -0.06
    POSITIVE LOGITS
    ;'
    0.07
    VN
    0.07
    	js
    0.07
    ."'
    0.07
    /rem
    0.07
     '^
    0.07
     HashMap
    0.07
    意义上
    0.07
     KD
    0.07
    🚗
    0.07
    Activations Density 0.001%

    No Known Activations