© 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. 11-RESID-POST-AA
    11. 75853
    Prev
    Next
    INDEX
    Explanations

    accidents and fatalities

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ست
    -0.06
    我一直
    -0.06
    在我
    -0.06
    Mag
    -0.06
    rob
    -0.06
    istent
    -0.06
    人と
    -0.06
    十月
    -0.06
    HasKey
    -0.06
    nat
    -0.06
    POSITIVE LOGITS
    فرق
    0.09
     ofs
    0.08
     ammunition
    0.07
     ions
    0.07
     schemas
    0.07
     chí
    0.07
     initiate
    0.07
    קים
    0.07
    厂家
    0.07
     FHA
    0.07
    Activations Density 0.071%

    No Known Activations