© 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. 15-RESID-POST-AA
    11. 23796
    Prev
    Next
    INDEX
    Explanations

    file

    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
    뛸
    -0.08
     cropping
    -0.07
    edback
    -0.07
     },↵
    -0.07
    acción
    -0.07
    뛰
    -0.07
    "}↵
    -0.07
    swick
    -0.07
    aksi
    -0.07
    捨
    -0.07
    POSITIVE LOGITS
    	real
    0.08
     interviewer
    0.08
    �
    0.07
    约谈
    0.07
     bệnh
    0.07
    気になる
    0.07
     peeled
    0.07
     leaning
    0.07
    𬺓
    0.07
     Miracle
    0.06
    Activations Density 0.008%

    No Known Activations