© 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. 130098
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    的日子
    -0.07
    ;s
    -0.07
     mir
    -0.07
     seu
    -0.07
    搠
    -0.07
    normalized
    -0.07
    ALTH
    -0.07
    -resolution
    -0.07
     folded
    -0.07
    突如其
    -0.07
    POSITIVE LOGITS
     piano
    0.07
     ApiService
    0.07
    Ca
    0.07
     ice
    0.07
    طا
    0.07
    olynomial
    0.07
    sti
    0.07
    ge
    0.06
    geist
    0.06
    .statusText
    0.06
    Activations Density 0.135%

    No Known Activations