Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 121390
    Prev
    Next
    INDEX
    Explanations

    URL

    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
    .clientX
    -0.07
    _triggered
    -0.07
    ueil
    -0.07
    🦚
    -0.07
    绿茶
    -0.07
    葡京
    -0.07
    printw
    -0.06
    \Input
    -0.06
     çevre
    -0.06
    大火
    -0.06
    POSITIVE LOGITS
    	q
    0.07
    -sp
    0.07
     Matching
    0.07
     Past
    0.07
     Chall
    0.07
     }}"
    0.06
    Ֆ
    0.06
     earm
    0.06
     RM
    0.06
    {}]
    0.06
    Activations Density 0.017%

    No Known Activations